ros/autocoder
1
0
Fork 0
mirror of https://github.com/leonvanzyl/autocoder.git synced 2026-02-02 07:23:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

refactor: optimize token usage, deduplicate code, fix bugs across agents

Browse Source 
Token reduction (~40% per session, ~2.3M fewer tokens per 200-feature project):
- Agent-type-specific tool lists: coding 9, testing 5, init 5 (was 19 for all)
- Right-sized max_turns: coding 300, testing 100 (was 1000 for all)
- Trimmed coding prompt template (~150 lines removed)
- Streamlined testing prompt with batch support
- YOLO mode now strips browser testing instructions from prompt
- Added Grep, WebFetch, WebSearch to expand project session

Performance improvements:
- Rate limit retries start at ~15s with jitter (was fixed 60s)
- Post-spawn delay reduced to 0.5s (was 2s)
- Orchestrator consolidated to 1 DB query per loop (was 5-7)
- Testing agents batch 3 features per session (was 1)
- Smart context compaction preserves critical state, discards noise

Bug fixes:
- Removed ghost feature_release_testing MCP tool (wasted tokens every test session)
- Forward all 9 Vertex AI env vars to chat sessions (was missing 3)
- Fix DetachedInstanceError risk in test batch ORM access
- Prevent duplicate testing of same features in parallel mode

Code deduplication:
- _get_project_path(): 9 copies -> 1 shared utility (project_helpers.py)
- validate_project_name(): 9 copies -> 2 variants in 1 file (validation.py)
- ROOT_DIR: 10 copies -> 1 definition (chat_constants.py)
- API_ENV_VARS: 4 copies -> 1 source of truth (env_constants.py)

Security hardening:
- Unified sensitive directory blocklist (14 dirs, was two divergent lists)
- Cached get_blocked_paths() for O(1) directory listing checks
- Terminal security warning when ALLOW_REMOTE=1 exposes WebSocket
- 20 new security tests for EXTRA_READ_PATHS blocking
- Extracted _validate_command_list() and _validate_pkill_processes() helpers

Type safety:
- 87 mypy errors -> 0 across 58 source files
- Installed types-PyYAML for proper yaml stub types
- Fixed SQLAlchemy Column[T] coercions across all routers

Dead code removed:
- 13 files deleted (~2,679 lines): unused UI components, debug logs, outdated docs
- 7 unused npm packages removed (Radix UI components with 0 imports)
- AgentAvatar.tsx reduced from 615 -> 119 lines (SVGs extracted to mascotData.tsx)

New CLI options:
- --testing-batch-size (1-5) for parallel mode test batching
- --testing-feature-ids for direct multi-feature testing

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Auto
2026-02-01 13:16:24 +02:00
parent dc5bcc4ae9
commit 94e0b05cb1
57 changed files with 1974 additions and 4300 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
server/services/assistant_chat_session.py
View File

@@ -25,25 +25,13 @@ from .assistant_database import (
create_conversation,
get_messages,
)
from .chat_constants import API_ENV_VARS, ROOT_DIR
# Load environment variables from .env file if present
load_dotenv()
logger = logging.getLogger(__name__)
# Root directory of the project
ROOT_DIR = Path(__file__).parent.parent.parent
# Environment variables to pass through to Claude CLI for API configuration
API_ENV_VARS = [
"ANTHROPIC_BASE_URL",
"ANTHROPIC_AUTH_TOKEN",
"API_TIMEOUT_MS",
"ANTHROPIC_DEFAULT_SONNET_MODEL",
"ANTHROPIC_DEFAULT_OPUS_MODEL",
"ANTHROPIC_DEFAULT_HAIKU_MODEL",
]
# Read-only feature MCP tools
READONLY_FEATURE_MCP_TOOLS = [
"mcp__features__feature_get_stats",
@@ -215,7 +203,7 @@ class AssistantChatSession:
# Create a new conversation if we don't have one
if is_new_conversation:
conv = create_conversation(self.project_dir, self.project_name)
self.conversation_id = conv.id
self.conversation_id = int(conv.id) # type coercion: Column[int] -> int
yield {"type": "conversation_created", "conversation_id": self.conversation_id}
# Build permissions list for assistant access (read + feature management)
@@ -270,7 +258,11 @@ class AssistantChatSession:
system_cli = shutil.which("claude")
# Build environment overrides for API configuration
sdk_env = {var: os.getenv(var) for var in API_ENV_VARS if os.getenv(var)}
sdk_env: dict[str, str] = {}
for var in API_ENV_VARS:
value = os.getenv(var)
if value:
sdk_env[var] = value
# Determine model from environment or use default
# This allows using alternative APIs (e.g., GLM via z.ai) that may not support Claude model names
@@ -286,7 +278,7 @@ class AssistantChatSession:
# This avoids Windows command line length limit (~8191 chars)
setting_sources=["project"],
allowed_tools=[*READONLY_BUILTIN_TOOLS, *ASSISTANT_FEATURE_TOOLS],
mcp_servers=mcp_servers,
mcp_servers=mcp_servers, # type: ignore[arg-type] # SDK accepts dict config at runtime
permission_mode="bypassPermissions",
max_turns=100,
cwd=str(self.project_dir.resolve()),
@@ -312,6 +304,8 @@ class AssistantChatSession:
greeting = f"Hello! I'm your project assistant for **{self.project_name}**. I can help you understand the codebase, explain features, and answer questions about the project. What would you like to know?"
# Store the greeting in the database
# conversation_id is guaranteed non-None here (set on line 206 above)
assert self.conversation_id is not None
add_message(self.project_dir, self.conversation_id, "assistant", greeting)
yield {"type": "text", "content": greeting}

3
server/services/assistant_database.py
View File

@@ -13,6 +13,7 @@ from pathlib import Path
from typing import Optional
from sqlalchemy import Column, DateTime, ForeignKey, Integer, String, Text, create_engine, func
from sqlalchemy.engine import Engine
from sqlalchemy.orm import DeclarativeBase, relationship, sessionmaker
logger = logging.getLogger(__name__)
@@ -23,7 +24,7 @@ class Base(DeclarativeBase):
# Engine cache to avoid creating new engines for each request
# Key: project directory path (as posix string), Value: SQLAlchemy engine
_engine_cache: dict[str, object] = {}
_engine_cache: dict[str, Engine] = {}
# Lock for thread-safe access to the engine cache
# Prevents race conditions when multiple threads create engines simultaneously

57
server/services/chat_constants.py Normal file
View File

@@ -0,0 +1,57 @@
"""
Chat Session Constants
======================
Shared constants for all chat session types (assistant, spec, expand).
The canonical ``API_ENV_VARS`` list lives in ``env_constants.py`` at the
project root and is re-exported here for convenience so that existing
imports (``from .chat_constants import API_ENV_VARS``) continue to work.
"""
import sys
from pathlib import Path
from typing import AsyncGenerator
# -------------------------------------------------------------------
# Root directory of the autocoder project (repository root).
# Used throughout the server package whenever the repo root is needed.
# -------------------------------------------------------------------
ROOT_DIR = Path(__file__).parent.parent.parent
# Ensure the project root is on sys.path so we can import env_constants
# from the root-level module without requiring a package install.
_root_str = str(ROOT_DIR)
if _root_str not in sys.path:
sys.path.insert(0, _root_str)
# -------------------------------------------------------------------
# Environment variables forwarded to Claude CLI subprocesses.
# Single source of truth lives in env_constants.py at the project root.
# Re-exported here so existing ``from .chat_constants import API_ENV_VARS``
# imports continue to work unchanged.
# -------------------------------------------------------------------
from env_constants import API_ENV_VARS # noqa: E402, F401
async def make_multimodal_message(content_blocks: list[dict]) -> AsyncGenerator[dict, None]:
"""Yield a single multimodal user message in Claude Agent SDK format.
The Claude Agent SDK's ``query()`` method accepts either a plain string
or an ``AsyncIterable[dict]`` for custom message formats. This helper
wraps a list of content blocks (text and/or images) in the expected
envelope.
Args:
content_blocks: List of content-block dicts, e.g.
``[{"type": "text", "text": "..."}, {"type": "image", ...}]``.
Yields:
A single dict representing the user message.
"""
yield {
"type": "user",
"message": {"role": "user", "content": content_blocks},
"parent_tool_use_id": None,
"session_id": "default",
}

45
server/services/expand_chat_session.py
View File

@@ -16,28 +16,19 @@ import threading
import uuid
from datetime import datetime
from pathlib import Path
from typing import AsyncGenerator, Optional
from typing import Any, AsyncGenerator, Optional
from claude_agent_sdk import ClaudeAgentOptions, ClaudeSDKClient
from dotenv import load_dotenv
from ..schemas import ImageAttachment
from .chat_constants import API_ENV_VARS, ROOT_DIR, make_multimodal_message
# Load environment variables from .env file if present
load_dotenv()
logger = logging.getLogger(__name__)
# Environment variables to pass through to Claude CLI for API configuration
API_ENV_VARS = [
"ANTHROPIC_BASE_URL",
"ANTHROPIC_AUTH_TOKEN",
"API_TIMEOUT_MS",
"ANTHROPIC_DEFAULT_SONNET_MODEL",
"ANTHROPIC_DEFAULT_OPUS_MODEL",
"ANTHROPIC_DEFAULT_HAIKU_MODEL",
]
# Feature MCP tools needed for expand session
EXPAND_FEATURE_TOOLS = [
"mcp__features__feature_create",
@@ -46,22 +37,6 @@ EXPAND_FEATURE_TOOLS = [
]
async def _make_multimodal_message(content_blocks: list[dict]) -> AsyncGenerator[dict, None]:
"""
Create an async generator that yields a properly formatted multimodal message.
"""
yield {
"type": "user",
"message": {"role": "user", "content": content_blocks},
"parent_tool_use_id": None,
"session_id": "default",
}
# Root directory of the project
ROOT_DIR = Path(__file__).parent.parent.parent
class ExpandChatSession:
"""
Manages a project expansion conversation.
@@ -179,7 +154,12 @@ class ExpandChatSession:
system_prompt = skill_content.replace("$ARGUMENTS", project_path)
# Build environment overrides for API configuration
sdk_env = {var: os.getenv(var) for var in API_ENV_VARS if os.getenv(var)}
# Filter to only include vars that are actually set (non-None)
sdk_env: dict[str, str] = {}
for var in API_ENV_VARS:
value = os.getenv(var)
if value:
sdk_env[var] = value
# Determine model from environment or use default
# This allows using alternative APIs (e.g., GLM via z.ai) that may not support Claude model names
@@ -207,9 +187,12 @@ class ExpandChatSession:
allowed_tools=[
"Read",
"Glob",
"Grep",
"WebFetch",
"WebSearch",
*EXPAND_FEATURE_TOOLS,
],
mcp_servers=mcp_servers,
mcp_servers=mcp_servers, # type: ignore[arg-type] # SDK accepts dict config at runtime
permission_mode="bypassPermissions",
max_turns=100,
cwd=str(self.project_dir.resolve()),
@@ -303,7 +286,7 @@ class ExpandChatSession:
# Build the message content
if attachments and len(attachments) > 0:
content_blocks = []
content_blocks: list[dict[str, Any]] = []
if message:
content_blocks.append({"type": "text", "text": message})
for att in attachments:
@@ -315,7 +298,7 @@ class ExpandChatSession:
"data": att.base64Data,
}
})
await self.client.query(_make_multimodal_message(content_blocks))
await self.client.query(make_multimodal_message(content_blocks))
logger.info(f"Sent multimodal message with {len(attachments)} image(s)")
else:
await self.client.query(message)

4
server/services/process_manager.py
View File

@@ -15,7 +15,7 @@ import sys
import threading
from datetime import datetime
from pathlib import Path
from typing import Awaitable, Callable, Literal, Set
from typing import Any, Awaitable, Callable, Literal, Set
import psutil
@@ -353,7 +353,7 @@ class AgentProcessManager:
# stdin=DEVNULL prevents blocking if Claude CLI or child process tries to read stdin
# CREATE_NO_WINDOW on Windows prevents console window pop-ups
# PYTHONUNBUFFERED ensures output isn't delayed
popen_kwargs = {
popen_kwargs: dict[str, Any] = {
"stdin": subprocess.DEVNULL,
"stdout": subprocess.PIPE,
"stderr": subprocess.STDOUT,

50
server/services/spec_chat_session.py
View File

@@ -13,49 +13,19 @@ import shutil
import threading
from datetime import datetime
from pathlib import Path
from typing import AsyncGenerator, Optional
from typing import Any, AsyncGenerator, Optional
from claude_agent_sdk import ClaudeAgentOptions, ClaudeSDKClient
from dotenv import load_dotenv
from ..schemas import ImageAttachment
from .chat_constants import API_ENV_VARS, ROOT_DIR, make_multimodal_message
# Load environment variables from .env file if present
load_dotenv()
logger = logging.getLogger(__name__)
# Environment variables to pass through to Claude CLI for API configuration
API_ENV_VARS = [
"ANTHROPIC_BASE_URL",
"ANTHROPIC_AUTH_TOKEN",
"API_TIMEOUT_MS",
"ANTHROPIC_DEFAULT_SONNET_MODEL",
"ANTHROPIC_DEFAULT_OPUS_MODEL",
"ANTHROPIC_DEFAULT_HAIKU_MODEL",
]
async def _make_multimodal_message(content_blocks: list[dict]) -> AsyncGenerator[dict, None]:
"""
Create an async generator that yields a properly formatted multimodal message.
The Claude Agent SDK's query() method accepts either:
- A string (simple text)
- An AsyncIterable[dict] (for custom message formats)
This function wraps content blocks in the expected message format.
"""
yield {
"type": "user",
"message": {"role": "user", "content": content_blocks},
"parent_tool_use_id": None,
"session_id": "default",
}
# Root directory of the project
ROOT_DIR = Path(__file__).parent.parent.parent
class SpecChatSession:
"""
@@ -170,7 +140,12 @@ class SpecChatSession:
system_cli = shutil.which("claude")
# Build environment overrides for API configuration
sdk_env = {var: os.getenv(var) for var in API_ENV_VARS if os.getenv(var)}
# Filter to only include vars that are actually set (non-None)
sdk_env: dict[str, str] = {}
for var in API_ENV_VARS:
value = os.getenv(var)
if value:
sdk_env[var] = value
# Determine model from environment or use default
# This allows using alternative APIs (e.g., GLM via z.ai) that may not support Claude model names
@@ -292,7 +267,7 @@ class SpecChatSession:
# Build the message content
if attachments and len(attachments) > 0:
# Multimodal message: build content blocks array
content_blocks = []
content_blocks: list[dict[str, Any]] = []
# Add text block if there's text
if message:
@@ -311,7 +286,7 @@ class SpecChatSession:
# Send multimodal content to Claude using async generator format
# The SDK's query() accepts AsyncIterable[dict] for custom message formats
await self.client.query(_make_multimodal_message(content_blocks))
await self.client.query(make_multimodal_message(content_blocks))
logger.info(f"Sent multimodal message with {len(attachments)} image(s)")
else:
# Text-only message: use string format
@@ -320,7 +295,7 @@ class SpecChatSession:
current_text = ""
# Track pending writes for BOTH required files
pending_writes = {
pending_writes: dict[str, dict[str, Any] | None] = {
"app_spec": None, # {"tool_id": ..., "path": ...}
"initializer": None, # {"tool_id": ..., "path": ...}
}
@@ -395,7 +370,8 @@ class SpecChatSession:
logger.warning(f"Tool error: {content}")
# Clear any pending writes that failed
for key in pending_writes:
if pending_writes[key] and tool_use_id == pending_writes[key].get("tool_id"):
pending_write = pending_writes[key]
if pending_write is not None and tool_use_id == pending_write.get("tool_id"):
logger.error(f"{key} write failed: {content}")
pending_writes[key] = None
else:

4
server/services/terminal_manager.py
View File

@@ -371,7 +371,7 @@ class TerminalSession:
# Reap zombie if not already reaped
if self._child_pid is not None:
try:
os.waitpid(self._child_pid, os.WNOHANG)
os.waitpid(self._child_pid, os.WNOHANG) # type: ignore[attr-defined] # Unix-only method, guarded by runtime platform selection
except ChildProcessError:
pass
except Exception:
@@ -736,7 +736,7 @@ async def cleanup_all_terminals() -> None:
Called on server shutdown to ensure all PTY processes are terminated.
"""
with _sessions_lock:
all_sessions = []
all_sessions: list[TerminalSession] = []
for project_sessions in _sessions.values():
all_sessions.extend(project_sessions.values())