open-swe/agent/tools/enter_plan_mode.py
Adam Moussa b3b0274403
feat: Re-land deferred upstream features on modular webhooks (#80) (#128)
* fix(webhooks): fall back to vision model for Slack/Linear image threads

Re-land upstream #1626 onto the modular webhook structure. When a
Slack mention or Linear issue carries images but the resolved model is
text-only, fall back to a vision-capable model instead of dropping the
images. Re-points default_vision_model_pair at the fork's image-capable
models (Opus 4.8 default, else any supports_images model) rather than
upstream's openai:/anthropic: provider filter.

Refs #80, upstream #1626

* fix(slack): persist trace_message_ts so web-handoff updates the trace reply

Re-land upstream #1630 onto the modular structure. The first-mention
store_slack_run_mapping call did not pass trace_message_ts, so it was
never persisted (nothing to preserve from on first mention) and
_notify_slack_web_handoff always skipped the trace-reply update on web
handoff. Pass it through and cover it with a test.

Refs #80, upstream #1630

* feat(slack): include channel context in Slack prompts

Re-land upstream #1633 onto the modular structure. Fetch cached Slack
channel metadata once per event (_get_slack_channel_context) and thread
it through the docs-plz gate, repo resolution, and process_slack_mention
so prompts carry the channel name and a clearly-marked untrusted
channel description. Avoids duplicate conversations.info calls.

Refs #80, upstream #1633

* feat(tools): add slack_start_new_thread breakout tool

Re-land upstream #1638 onto the modular structure. Adds the
slack_start_new_thread tool (posts a top-level Slack message and
dispatches a fresh agent run for a broken-out task via the durable
dispatch_agent_run contract), wires it into the agent tool list and
tools/__init__, adds prompt guidance, and excludes it from plan mode so
it can't bypass the approval flow. Tool imports only live modules.

Refs #80, upstream #1638

* feat(plan): notify Slack on plan approval

Re-land upstream #1632 onto the modular structure. When a plan is
approved via the dashboard approve endpoint, post a thread reply to the
originating Slack thread noting the comment count and approver, after
the follow-up run is dispatched. Slack post failures never break
approval. Adapted to the fork's approve_plan (no plan_markdown read).

Refs #80, upstream #1632

* feat(plan): publish plans from sandbox files

Re-land upstream #1635 onto the modular structure, completing the
partially-ported change so dev is internally consistent. save_plan now
takes a plan_file_path, reads the agent-authored Markdown file from
/workspace/plans/ (validating extension/location/UTF-8/size) and
publishes it, instead of taking a plan_markdown string. Removes
write_file/edit_file from PLAN_MODE_EXCLUDED_TOOLS so the agent can
author the plan file, updates enter_plan_mode/reject_plan guidance and
the e2e fake LLM. Skips the #1610-only update_plan hunk (not on dev).

Refs #80, upstream #1635

* fix(security): SSRF-harden server-side image fetch + stop logging raw image URLs

INJ-01 (high): fetch_image_block used follow_redirects=True with no per-hop
revalidation and discarded the resolved-IP pin, so an attacker-authored Slack/
Linear image URL could 302-redirect the fetch to an internal host / cloud
metadata endpoint (blind SSRF), and DNS-rebinding could bypass the one-shot
is_url_safe check. Route image fetches through the same per-hop resolve+pin+
revalidate loop the http_request tool uses, lifted into url_safety as the shared
request_with_safe_redirects. Also strip the per-host Slack/Linear bearer token
on redirect so it can't be replayed to a redirect target.

SC-1 (low): linear.py logged full image URLs (which can carry signed tokens) at
DEBUG; multimodal logged them at INFO on every fetch. Log host-only.

Sink lived in multimodal.py (unchanged by the feature work) but PR #128 widened
its reach by no longer dropping images for text-only models. Fixing on the base
branch so #130/#129 inherit it on rebase. Adds fetch_image_block SSRF regression
tests (redirect-to-internal blocked; auth stripped on redirect).
2026-07-08 18:32:43 -04:00

63 lines
2.5 KiB
Python

"""Tool: ``enter_plan_mode``. Switch the run into read-only planning."""
from __future__ import annotations
import logging
from typing import Annotated
from langchain_core.messages import ToolMessage
from langchain_core.tools import InjectedToolCallId
from langgraph.config import get_config
from langgraph.types import Command
from ..dashboard.plan_store import PLAN_STATUS_PLANNING, set_plan_status
logger = logging.getLogger(__name__)
_ENTERED_MESSAGE = (
"Plan mode is active. Stay read-only for the target repo: research the codebase, "
"create or edit a dated, concise plan file under `/workspace/plans/`, then publish "
"it with the `save_plan` tool and share the plan-review link in the source channel. "
"Do not edit repo files, commit, push, or open a PR — wait for the user to approve "
"the plan."
)
async def enter_plan_mode(tool_call_id: Annotated[str, InjectedToolCallId]) -> Command:
"""Activate plan mode mid-run.
Call this when you believe the task would benefit from a structured
implementation plan before writing any code — e.g. when the request is
complex, touches many files, or has multiple valid approaches. This is
NOT triggered by the word "plan" appearing in the request; use your
judgment about whether planning is genuinely warranted.
Once activated, stay read-only for the target repo: research the codebase,
create or edit a dated, concise Markdown plan outside any repo (for example,
``/workspace/plans/YYYY-MM-DD-short-task-slug.md``), then publish it with
the ``save_plan`` tool and share the plan-review link with the user. Do not
edit repo files, commit, push, or open a PR — the user reviews the plan and
approves it before you implement.
"""
thread_id = _thread_id_from_config()
if thread_id:
try:
await set_plan_status(thread_id, PLAN_STATUS_PLANNING, plan_mode=True)
except Exception:
logger.warning("Failed to persist plan-mode entry for %s", thread_id, exc_info=True)
return Command(
update={
"plan_mode": True,
"messages": [ToolMessage(content=_ENTERED_MESSAGE, tool_call_id=tool_call_id)],
}
)
def _thread_id_from_config() -> str | None:
try:
config = get_config()
except Exception:
return None
configurable = config.get("configurable", {}) if isinstance(config, dict) else {}
thread_id = configurable.get("thread_id") if isinstance(configurable, dict) else None
return str(thread_id) if thread_id else None