refactor(tools): register update_plan tool and support dynamic execution (#4069)

* refactor(tools): register update_plan tool and support dynamic execution

* refactor: move interaction tools to registry and fix tuple unpacking error

* docs: add HACK comment for circular dependency workaround

Signed-off-by: dewanggaabdullah <255674162+dewanggaabdullah@users.noreply.github.com>

* refactor(tools): use docstring for better code style

Signed-off-by: dewanggaabdullah <255674162+dewanggaabdullah@users.noreply.github.com>

* fix(tools & file): restore file tool_registry & unknown tool fallback and fix dynamic handlers unpacking

Signed-off-by: dewanggaabdullah <255674162+dewanggaabdullah@users.noreply.github.com>

---------

Signed-off-by: dewanggaabdullah <255674162+dewanggaabdullah@users.noreply.github.com>
This commit is contained in:
Dewangga Abdullah
2026-06-27 22:36:10 +07:00
committed by GitHub
parent 2dfc83ee22
commit 6d429a49b9
3 changed files with 132 additions and 82 deletions
+3
View File
@@ -22,6 +22,7 @@ from .subprocess_tools import BashTool, PythonTool
from .web_tools import WebSearchTool, WebFetchTool
from .filesystem_tools import ReadFileTool, WriteFileTool, EditFileTool, LsTool, GlobTool, GrepTool, GetWorkspaceTool
from .document_tools import CreateDocumentTool, UpdateDocumentTool, EditDocumentTool, SuggestDocumentTool, ManageDocumentTool
from .interaction_tools import AskUserTool, UpdatePlanTool
from .model_interaction_tools import ChatWithModelTool, AskTeacherTool, ListModelsTool
from .bg_job_tools import ManageBgJobsTool
from .session_tools import CreateSessionTool, ListSessionsTool, SendToSessionTool, ManageSessionTool
@@ -48,6 +49,8 @@ TOOL_HANDLERS = {
"suggest_document": SuggestDocumentTool().execute,
"manage_documents": ManageDocumentTool().execute,
"get_workspace": GetWorkspaceTool().execute,
"ask_user": AskUserTool().execute,
"update_plan": UpdatePlanTool().execute,
"chat_with_model": ChatWithModelTool().execute,
"ask_teacher": AskTeacherTool().execute,
"list_models": ListModelsTool().execute,
+95
View File
@@ -0,0 +1,95 @@
import json
import logging
logger = logging.getLogger(__name__)
class AskUserTool:
async def execute(self, content, ctx):
"""
ask_user: the agent poses a multiple-choice question to the user to get a
decision/clarification. This is a pure UI-control marker — no subprocess,
no filesystem. It returns an `ask_user` payload that the agent loop turns
into an `ask_user` SSE event and then ENDS the turn, so the chat waits for
the user's selection (their choice arrives as the next message).
"""
question, options, multi = "", [], False
raw = (content or "").strip()
try:
parsed = json.loads(raw) if raw else {}
except (ValueError, TypeError):
parsed = {}
if isinstance(parsed, dict):
question = str(parsed.get("question", "")).strip()
multi = bool(parsed.get("multi") or parsed.get("multiSelect"))
for opt in (parsed.get("options") or []):
if isinstance(opt, dict):
label = str(opt.get("label", "")).strip()
descr = str(opt.get("description", "")).strip()
elif isinstance(opt, str):
label, descr = opt.strip(), ""
else:
continue
if label:
options.append({"label": label, "description": descr})
else:
question = raw
if not question or len(options) < 2:
return "ask_user: invalid", {
"error": (
"ask_user needs a non-empty `question` and at least 2 `options` "
"(each an object with a `label`, optional `description`)."
),
"exit_code": 1,
}
options = options[:6] # keep the choice list sane
desc = f"ask_user: {question[:80]}"
labels = ", ".join(o["label"] for o in options)
result = {
"ask_user": {"question": question, "options": options, "multi": multi},
"output": f"Asked the user: {question}\nOptions: {labels}\nAwaiting their selection.",
"exit_code": 0,
}
logger.info("Tool executed: %s (%d options, multi=%s)", desc, len(options), multi)
return desc, result
class UpdatePlanTool:
async def execute(self, content, ctx):
"""
update_plan: the agent writes back to the active plan — tick an item done
or revise steps (e.g. when the user asks to change something). Pure UI
marker: returns a `plan_update` payload the agent loop turns into a
`plan_update` SSE event; the frontend replaces the stored plan and refreshes
the docked plan window. Does NOT end the turn.
"""
raw = (content or "").strip()
plan = ""
try:
parsed = json.loads(raw) if raw else {}
except (ValueError, TypeError):
parsed = {}
if isinstance(parsed, dict) and parsed.get("plan"):
plan = str(parsed.get("plan", "")).strip()
else:
plan = raw
if not plan:
return "update_plan: invalid", {
"error": "update_plan needs a non-empty `plan` (the full updated checklist as markdown).",
"exit_code": 1,
}
plan = plan[:8192]
done = plan.count("- [x]") + plan.count("- [X]")
total = done + plan.count("- [ ]")
desc = f"update_plan: {done}/{total} done" if total else "update_plan"
result = {
"plan_update": {"plan": plan},
"output": f"Plan updated ({done}/{total} steps complete)." if total else "Plan updated.",
"exit_code": 0,
}
logger.info("Tool executed: %s", desc)
return desc, result
+34 -82
View File
@@ -535,7 +535,7 @@ async def execute_tool_block(
"""
token = _active_workspace.set(workspace or None)
try:
return await _execute_tool_block_impl(
output = await _execute_tool_block_impl(
block,
session_id=session_id,
disabled_tools=disabled_tools,
@@ -543,6 +543,7 @@ async def execute_tool_block(
progress_cb=progress_cb,
tool_policy=tool_policy,
)
return output
finally:
_active_workspace.reset(token)
@@ -576,6 +577,22 @@ async def _execute_tool_block_impl(
do_app_api,
)
# HACK:
# This is a temporary workaround for a circular dependency between
# tool_execution.py and agent_tools.__init__.py.
#
# See issue #4277:
# refactor(tools): Move the registry from __init__.py into a
# dedicated registry.py module.
#
# Do not copy this pattern elsewhere. This import should be removed
# once the registry refactor is completed.
try:
agent_tools_mod = __import__("src.agent_tools", fromlist=["TOOL_HANDLERS"])
dynamic_handlers = getattr(agent_tools_mod, "TOOL_HANDLERS", {})
except ImportError:
dynamic_handlers = {}
tool = block.tool_type
content = block.content
@@ -639,86 +656,6 @@ async def _execute_tool_block_impl(
logger.warning("Public tool policy blocked owner=%r tool=%s", owner, tool)
return desc, result
# ask_user: the agent poses a multiple-choice question to the user to get a
# decision/clarification. This is a pure UI-control marker — no subprocess,
# no filesystem. It returns an `ask_user` payload that the agent loop turns
# into an `ask_user` SSE event and then ENDS the turn, so the chat waits for
# the user's selection (their choice arrives as the next message).
if tool == "ask_user":
question, options, multi = "", [], False
raw = (content or "").strip()
try:
parsed = json.loads(raw) if raw else {}
except (ValueError, TypeError):
parsed = {}
if isinstance(parsed, dict):
question = str(parsed.get("question", "")).strip()
multi = bool(parsed.get("multi") or parsed.get("multiSelect"))
for opt in (parsed.get("options") or []):
if isinstance(opt, dict):
label = str(opt.get("label", "")).strip()
descr = str(opt.get("description", "")).strip()
elif isinstance(opt, str):
label, descr = opt.strip(), ""
else:
continue
if label:
options.append({"label": label, "description": descr})
else:
question = raw
if not question or len(options) < 2:
return "ask_user: invalid", {
"error": (
"ask_user needs a non-empty `question` and at least 2 `options` "
"(each an object with a `label`, optional `description`)."
),
"exit_code": 1,
}
options = options[:6] # keep the choice list sane
desc = f"ask_user: {question[:80]}"
labels = ", ".join(o["label"] for o in options)
result = {
"ask_user": {"question": question, "options": options, "multi": multi},
"output": f"Asked the user: {question}\nOptions: {labels}\nAwaiting their selection.",
"exit_code": 0,
}
logger.info("Tool executed: %s (%d options, multi=%s)", desc, len(options), multi)
return desc, result
# update_plan: the agent writes back to the active plan — tick an item done
# or revise steps (e.g. when the user asks to change something). Pure UI
# marker: returns a `plan_update` payload the agent loop turns into a
# `plan_update` SSE event; the frontend replaces the stored plan and refreshes
# the docked plan window. Does NOT end the turn.
if tool == "update_plan":
import json as _json
raw = (content or "").strip()
plan = ""
try:
parsed = _json.loads(raw) if raw else {}
except (ValueError, TypeError):
parsed = {}
if isinstance(parsed, dict) and parsed.get("plan"):
plan = str(parsed.get("plan", "")).strip()
else:
# Plain-string call (raw checklist) or JSON without a usable `plan`.
plan = raw
if not plan:
return "update_plan: invalid", {
"error": "update_plan needs a non-empty `plan` (the full updated checklist as markdown).",
"exit_code": 1,
}
plan = plan[:8192]
done = plan.count("- [x]") + plan.count("- [X]")
total = done + plan.count("- [ ]")
desc = f"update_plan: {done}/{total} done" if total else "update_plan"
result = {
"plan_update": {"plan": plan},
"output": f"Plan updated ({done}/{total} steps complete)." if total else "Plan updated.",
"exit_code": 0,
}
logger.info("Tool executed: %s", desc)
return desc, result
# Background execution: a `bash` block whose first line is the `#!bg`
# marker runs DETACHED — returns a job id immediately so the chat stream
@@ -902,9 +839,24 @@ async def _execute_tool_block_impl(
else:
desc = f"mcp: {tool}"
result = {"error": "MCP manager not available", "exit_code": 1}
elif tool in dynamic_handlers:
first_line = content.split(chr(10))[0][:80]
desc = f"registry: {tool} {first_line}".strip()
res = await _direct_fallback(tool, content, progress_cb=progress_cb)
if isinstance(res, tuple):
desc, result = res
else:
result = res or {"error": f"{tool}: execution failed", "exit_code": 1}
else:
desc = f"unknown: {tool}"
result = {"error": f"Unknown tool type: {tool}", "exit_code": 1}
result = {
"error": f"Unknown tool: {tool}",
"exit_code": 1
}
logger.info(f"Tool executed: {desc} -> exit_code={result.get('exit_code', 'n/a')}")
return desc, result