Merge branch 'main' into feat/google-scopes

Author: bryanadenhq

.github/workflows/ci.yml

@@ -62,8 +62,11 @@ jobs:
           uv run pytest tests/ -v
 
   test-tools:
-    name: Test Tools
-    runs-on: ubuntu-latest
+    name: Test Tools (${{ matrix.os }})
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-latest]
     steps:
       - uses: actions/checkout@v4
 

README.md

@@ -82,6 +82,7 @@ Use Hive when you need:
 
 - Python 3.11+ for agent development
 - An LLM provider that powers the agents
+- **ripgrep (optional, recommended on Windows):** The `search_files` tool uses ripgrep for faster file search. If not installed, a Python fallback is used. On Windows: `winget install BurntSushi.ripgrep` or `scoop install ripgrep`
 
 > **Note for Windows Users:** It is strongly recommended to use **WSL (Windows Subsystem for Linux)** or **Git Bash** to run this framework. Some core automation scripts may not execute correctly in standard Command Prompt or PowerShell.
 

core/framework/agents/hive_coder/nodes/__init__.py

@@ -46,6 +46,7 @@ def _build_appendices() -> str:
     "read_file",
     "write_file",
     "edit_file",
+    "hashline_edit",
     "list_directory",
     "search_files",
     "run_command",
@@ -55,8 +56,6 @@ def _build_appendices() -> str:
     "validate_agent_tools",
     "list_agents",
     "list_agent_sessions",
-    "get_agent_session_state",
-    "get_agent_session_memory",
     "list_agent_checkpoints",
     "get_agent_checkpoint",
     "run_agent_tests",
@@ -131,12 +130,23 @@ def _build_appendices() -> str:
 
 # Tools
 
+## Paths (MANDATORY)
+**Always use RELATIVE paths**
+(e.g. `exports/agent_name/config.py`, `exports/agent_name/nodes/__init__.py`).
+**Never use absolute paths** like `/mnt/data/...` or `/workspace/...` — they fail.
+The project root is implicit.
+
 ## File I/O
-- read_file(path, offset?, limit?) — read with line numbers
+- read_file(path, offset?, limit?, hashline?) — read with line numbers; \
+hashline=True for N:hhhh|content anchors (use with hashline_edit)
 - write_file(path, content) — create/overwrite, auto-mkdir
 - edit_file(path, old_text, new_text, replace_all?) — fuzzy-match edit
+- hashline_edit(path, edits, auto_cleanup?, encoding?) — anchor-based \
+editing using N:hhhh refs from read_file(hashline=True). Ops: set_line, \
+replace_lines, insert_after, insert_before, replace, append
 - list_directory(path, recursive?) — list contents
-- search_files(pattern, path?, include?) — regex search
+- search_files(pattern, path?, include?, hashline?) — regex search; \
+hashline=True for anchors in results
 - run_command(command, cwd?, timeout?) — shell execution
 - undo_changes(path?) — restore from git snapshot
 
@@ -149,8 +159,6 @@ def _build_appendices() -> str:
 in an agent's nodes actually exist. Call after building.
 - list_agents() — list all agent packages in exports/ with session counts
 - list_agent_sessions(agent_name, status?, limit?) — list sessions
-- get_agent_session_state(agent_name, session_id) — full session state
-- get_agent_session_memory(agent_name, session_id, key?) — memory data
 - list_agent_checkpoints(agent_name, session_id) — list checkpoints
 - get_agent_checkpoint(agent_name, session_id, checkpoint_id?) — load checkpoint
 - run_agent_tests(agent_name, test_types?, fail_fast?) — run pytest with parsing
@@ -185,8 +193,7 @@ def _build_appendices() -> str:
 ## Debugging Built Agents
 When a user says "my agent is failing" or "debug this agent":
 1. list_agent_sessions("{agent_name}") — find the session
-2. get_agent_session_state("{agent_name}", "{session_id}") — see status
-3. get_agent_session_memory("{agent_name}", "{session_id}") — inspect data
+2. get_worker_status
 4. list_agent_checkpoints / get_agent_checkpoint — trace execution
 
 # Agent Building Workflow
@@ -608,7 +615,7 @@ def _build_appendices() -> str:
 - File I/O: read_file, write_file, edit_file, list_directory, search_files, \
 run_command, undo_changes
 - Meta-agent: list_agent_tools, validate_agent_tools, \
-list_agents, list_agent_sessions, get_agent_session_state, get_agent_session_memory, \
+list_agents, list_agent_sessions, \
 list_agent_checkpoints, get_agent_checkpoint, run_agent_tests
 - load_built_agent(agent_path) — Load the agent and switch to STAGING mode
 - list_credentials(credential_id?) — List authorized credentials

core/framework/graph/executor.py

@@ -621,11 +621,14 @@ async def execute(
         # node doesn't restore a filled OutputAccumulator from the previous
         # webhook run (which would cause the judge to accept immediately).
         # The conversation history is preserved (continuous memory).
+        # Exclude cold restores — those need to continue the conversation
+        # naturally without a "start fresh" marker.
         _is_fresh_shared = bool(
             session_state
             and session_state.get("resume_session_id")
             and not session_state.get("paused_at")
             and not session_state.get("resume_from_checkpoint")
+            and not session_state.get("cold_restore")
         )
         if _is_fresh_shared and is_continuous and self._storage_path:
             try:

core/framework/mcp/agent_builder_server.py

@@ -2899,6 +2899,7 @@ def run_tests(
             text=True,
             timeout=600,  # 10 minute timeout
             env=env,
+            stdin=subprocess.DEVNULL,
         )
     except subprocess.TimeoutExpired:
         return json.dumps(
@@ -3091,6 +3092,7 @@ def debug_test(
             text=True,
             timeout=120,  # 2 minute timeout for single test
             env=env,
+            stdin=subprocess.DEVNULL,
         )
     except subprocess.TimeoutExpired:
         return json.dumps(
@@ -3714,82 +3716,6 @@ def list_agent_sessions(
     )
 
 
-@mcp.tool()
-def get_agent_session_state(
-    agent_work_dir: Annotated[str, "Path to the agent's working directory"],
-    session_id: Annotated[str, "The session ID (e.g., 'session_20260208_143022_abc12345')"],
-) -> str:
-    """
-    Load full session state for a specific session.
-
-    Returns complete session data including status, progress, result,
-    metrics, and checkpoint info. Memory values are excluded to prevent
-    context bloat -- use get_agent_session_memory to retrieve memory contents.
-    """
-    state_path = Path(agent_work_dir) / "sessions" / session_id / "state.json"
-    data = _read_session_json(state_path)
-    if data is None:
-        return json.dumps({"error": f"Session not found: {session_id}"})
-
-    memory = data.get("memory", {})
-    data["memory_keys"] = list(memory.keys()) if isinstance(memory, dict) else []
-    data["memory_size"] = len(memory) if isinstance(memory, dict) else 0
-    data.pop("memory", None)
-
-    return json.dumps(data, indent=2, default=str)
-
-
-@mcp.tool()
-def get_agent_session_memory(
-    agent_work_dir: Annotated[str, "Path to the agent's working directory"],
-    session_id: Annotated[str, "The session ID"],
-    key: Annotated[str, "Specific memory key to retrieve. Empty for all."] = "",
-) -> str:
-    """
-    Get memory contents from a session.
-
-    Memory stores intermediate results passed between nodes. Use this
-    to inspect what data was produced during execution.
-
-    If key is provided, returns only that memory key's value.
-    If key is empty, returns all memory keys and their values.
-    """
-    state_path = Path(agent_work_dir) / "sessions" / session_id / "state.json"
-    data = _read_session_json(state_path)
-    if data is None:
-        return json.dumps({"error": f"Session not found: {session_id}"})
-
-    memory = data.get("memory", {})
-    if not isinstance(memory, dict):
-        memory = {}
-
-    if key:
-        if key not in memory:
-            return json.dumps(
-                {
-                    "error": f"Memory key not found: '{key}'",
-                    "available_keys": list(memory.keys()),
-                }
-            )
-        value = memory[key]
-        return json.dumps(
-            {
-                "session_id": session_id,
-                "key": key,
-                "value": value,
-                "value_type": type(value).__name__,
-            },
-            indent=2,
-            default=str,
-        )
-
-    return json.dumps(
-        {"session_id": session_id, "memory": memory, "total_keys": len(memory)},
-        indent=2,
-        default=str,
-    )
-
-
 @mcp.tool()
 def list_agent_checkpoints(
     agent_work_dir: Annotated[str, "Path to the agent's working directory"],

core/framework/runner/mcp_client.py

@@ -7,6 +7,8 @@
 import asyncio
 import logging
 import os
+import sys
+import threading
 from dataclasses import dataclass, field
 from typing import Any, Literal
 
@@ -73,6 +75,8 @@ def __init__(self, config: MCPServerConfig):
         # Background event loop for persistent STDIO connection
         self._loop = None
         self._loop_thread = None
+        # Serialize STDIO tool calls (avoids races, helps on Windows)
+        self._stdio_call_lock = threading.Lock()
 
     def _run_async(self, coro):
         """
@@ -156,11 +160,19 @@ def _connect_stdio(self) -> None:
             # Create server parameters
             # Always inherit parent environment and merge with any custom env vars
             merged_env = {**os.environ, **(self.config.env or {})}
+            # On Windows, passing cwd can cause WinError 267 ("invalid directory name").
+            # tool_registry passes cwd=None and uses absolute script paths when applicable.
+            cwd = self.config.cwd
+            if os.name == "nt" and cwd is not None:
+                # Avoid passing cwd on Windows; tool_registry should have set cwd=None
+                # and absolute script paths for tools-dir servers. If cwd is still set,
+                # pass None to prevent WinError 267 (caller should use absolute paths).
+                cwd = None
             server_params = StdioServerParameters(
                 command=self.config.command,
                 args=self.config.args,
                 env=merged_env,
-                cwd=self.config.cwd,
+                cwd=cwd,
             )
 
             # Store for later use
@@ -184,10 +196,12 @@ async def init_connection():
                         from mcp.client.stdio import stdio_client
 
                         # Create persistent stdio client context.
-                        # Redirect server stderr to devnull to prevent raw
-                        # output from leaking behind the TUI.
-                        devnull = open(os.devnull, "w")  # noqa: SIM115
-                        self._stdio_context = stdio_client(server_params, errlog=devnull)
+                        # On Windows, use stderr so subprocess startup errors are visible.
+                        if os.name == "nt":
+                            errlog = sys.stderr
+                        else:
+                            errlog = open(os.devnull, "w")  # noqa: SIM115
+                        self._stdio_context = stdio_client(server_params, errlog=errlog)
                         (
                             self._read_stream,
                             self._write_stream,
@@ -353,7 +367,8 @@ def call_tool(self, tool_name: str, arguments: dict[str, Any]) -> Any:
             raise ValueError(f"Unknown tool: {tool_name}")
 
         if self.config.transport == "stdio":
-            return self._run_async(self._call_tool_stdio_async(tool_name, arguments))
+            with self._stdio_call_lock:
+                return self._run_async(self._call_tool_stdio_async(tool_name, arguments))
         else:
             return self._call_tool_http(tool_name, arguments)
 
@@ -448,11 +463,15 @@ async def _cleanup_stdio_async(self) -> None:
             if self._stdio_context:
                 await self._stdio_context.__aexit__(None, None, None)
         except asyncio.CancelledError:
-            logger.warning(
+            logger.debug(
                 "STDIO context cleanup was cancelled; proceeding with best-effort shutdown"
             )
         except Exception as e:
-            logger.warning(f"Error closing STDIO context: {e}")
+            msg = str(e).lower()
+            if "cancel scope" in msg or "different task" in msg:
+                logger.debug("STDIO context teardown (known anyio quirk): %s", e)
+            else:
+                logger.warning(f"Error closing STDIO context: {e}")
         finally:
             self._stdio_context = None