step 3.5 complete: chatbot journey endpoint
This commit is contained in:
317
app/api/routes/agent_setup.py
Normal file
317
app/api/routes/agent_setup.py
Normal file
@@ -0,0 +1,317 @@
|
||||
"""Chatbot Journey endpoints — guided conversation to build an agent prompt_template.
|
||||
|
||||
Endpoints:
|
||||
POST /agents/journey/start — start a new journey session
|
||||
POST /agents/journey/message — continue the conversation
|
||||
|
||||
Sessions are stored in-memory with a 30-minute TTL. Stale entries are
|
||||
cleaned up lazily on access. Upgrade to Redis for multi-instance deployments.
|
||||
|
||||
Journey flow:
|
||||
1. Client sends ``{ agent_type, agent_id? }`` to ``/start``.
|
||||
2. Server creates a session, calls the LLM with a contextual system prompt,
|
||||
and returns the first question.
|
||||
3. Client sends follow-up messages to ``/message``.
|
||||
4. After 3-5 turns the LLM wraps up by emitting a ``prompt_template`` block
|
||||
delimited by ``PROMPT_TEMPLATE_START`` / ``PROMPT_TEMPLATE_END``.
|
||||
5. Server parses the block, sets ``done=True``, and returns the template.
|
||||
|
||||
The ``prompt_template`` from the final response is meant to be stored in
|
||||
``LocalAgentConfig.prompt_template`` or ``CloudAgentConfig.prompt_template``
|
||||
by the Electron client (via the agent CRUD endpoints).
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import time
|
||||
import uuid
|
||||
from dataclasses import dataclass, field
|
||||
from typing import Any
|
||||
|
||||
from fastapi import APIRouter, Depends, HTTPException, status
|
||||
from langchain_core.messages import AIMessage, HumanMessage, SystemMessage
|
||||
from sqlalchemy import select
|
||||
from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.api.deps import get_current_user
|
||||
from app.core.llm import get_llm
|
||||
from app.db import get_session
|
||||
from app.models import CloudAgentConfig, LocalAgentConfig
|
||||
from app.schemas import (
|
||||
JourneyMessageRequest,
|
||||
JourneyResponse,
|
||||
JourneyStartRequest,
|
||||
UserProfile,
|
||||
)
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
router = APIRouter(prefix="/agents/journey", tags=["agents"])
|
||||
|
||||
# ── Session TTL ───────────────────────────────────────────────────────────
|
||||
|
||||
_SESSION_TTL_SECONDS: int = 1800 # 30 minutes
|
||||
|
||||
# Sentinel strings used to delimit the LLM-produced prompt_template.
|
||||
_TEMPLATE_START = "PROMPT_TEMPLATE_START"
|
||||
_TEMPLATE_END = "PROMPT_TEMPLATE_END"
|
||||
|
||||
# Maximum number of conversation turns before the LLM is nudged to wrap up.
|
||||
_MAX_TURNS: int = 5
|
||||
|
||||
# ── In-memory session store ───────────────────────────────────────────────
|
||||
|
||||
|
||||
@dataclass
|
||||
class _JourneySession:
|
||||
session_id: str
|
||||
user_id: str
|
||||
agent_type: str # "local" | "cloud"
|
||||
history: list[dict[str, Any]] = field(default_factory=list)
|
||||
created_at: float = field(default_factory=time.monotonic)
|
||||
|
||||
def is_expired(self) -> bool:
|
||||
return (time.monotonic() - self.created_at) > _SESSION_TTL_SECONDS
|
||||
|
||||
|
||||
# session_id → session
|
||||
_sessions: dict[str, _JourneySession] = {}
|
||||
|
||||
|
||||
def _get_session(session_id: str, user_id: str) -> _JourneySession:
|
||||
"""Retrieve session; raise 404 on missing, expired, or wrong owner."""
|
||||
s = _sessions.get(session_id)
|
||||
if s is None or s.is_expired():
|
||||
_sessions.pop(session_id, None)
|
||||
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Journey session not found or expired")
|
||||
if s.user_id != user_id:
|
||||
raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail="Journey session not found or expired")
|
||||
return s
|
||||
|
||||
|
||||
# ── System prompt builder ─────────────────────────────────────────────────
|
||||
|
||||
_LOCAL_PREAMBLE = """\
|
||||
What kind of files are in the directories you want to monitor? \
|
||||
(for example: emails saved as .eml, documents in .pdf or .txt, markdown notes, etc.)"""
|
||||
|
||||
_CLOUD_PREAMBLE = """\
|
||||
What kind of emails or messages should I look for? \
|
||||
(for example: client communications, invoices, meeting notes, project updates, etc.)"""
|
||||
|
||||
_SYSTEM_PROMPT_TEMPLATE = """\
|
||||
You are a friendly assistant helping a freelancer configure a data-extraction agent.
|
||||
Your job is to understand exactly what data the user wants to extract from their {source_description} \
|
||||
and produce a detailed prompt_template that a separate AI will use as its instruction set.
|
||||
|
||||
Ask concise, focused questions one at a time. Cover these topics (not necessarily in this order):
|
||||
1. The type and format of the source content.
|
||||
2. Which data types to extract: tasks, notes, checkpoints, and/or projects.
|
||||
3. How fields should be mapped (e.g. email subject → task title).
|
||||
4. Priority or status rules (e.g. "urgent" keyword → high priority).
|
||||
5. Any special handling, date extraction, or exclusions.
|
||||
|
||||
After 3-5 questions (when you have enough information), output the final prompt_template between \
|
||||
these exact markers on their own lines:
|
||||
|
||||
{template_start}
|
||||
<the complete extraction prompt here>
|
||||
{template_end}
|
||||
|
||||
The prompt_template must be a self-contained instruction for an AI that receives a document/email/message \
|
||||
and must return a JSON array of records in this shape:
|
||||
[{{ "table": "<tasks|notes|checkpoints|projects>", "data": {{ <field: value> }} }}, ...]
|
||||
|
||||
Rules for the generated template:
|
||||
- Be explicit about field names (camelCase: title, status, priority, dueDate, projectId, content, etc.).
|
||||
- Include concrete examples of mappings.
|
||||
- Mention that Electron adds id/createdAt/updatedAt automatically.
|
||||
- Set isAiSuggested: true and isApproved: false on every record.
|
||||
{existing_section}\
|
||||
Do not ask more than {max_turns} questions total. Start with your first question now.\
|
||||
"""
|
||||
|
||||
|
||||
def _build_system_prompt(agent_type: str, existing_template: str | None) -> str:
|
||||
source_description = (
|
||||
"files in local directories" if agent_type == "local" else "emails and messages from cloud providers"
|
||||
)
|
||||
existing_section = (
|
||||
f"\nThe user already has the following prompt_template — refine it based on their answers:\n"
|
||||
f"---\n{existing_template}\n---\n"
|
||||
if existing_template
|
||||
else ""
|
||||
)
|
||||
return _SYSTEM_PROMPT_TEMPLATE.format(
|
||||
source_description=source_description,
|
||||
template_start=_TEMPLATE_START,
|
||||
template_end=_TEMPLATE_END,
|
||||
existing_section=existing_section,
|
||||
max_turns=_MAX_TURNS,
|
||||
)
|
||||
|
||||
|
||||
def _first_question(agent_type: str) -> str:
|
||||
return _LOCAL_PREAMBLE if agent_type == "local" else _CLOUD_PREAMBLE
|
||||
|
||||
|
||||
# ── Template extraction ───────────────────────────────────────────────────
|
||||
|
||||
|
||||
def _extract_template(text: str) -> str | None:
|
||||
"""Return the text between PROMPT_TEMPLATE_START and PROMPT_TEMPLATE_END, or None."""
|
||||
if _TEMPLATE_START not in text or _TEMPLATE_END not in text:
|
||||
return None
|
||||
start_idx = text.index(_TEMPLATE_START) + len(_TEMPLATE_START)
|
||||
end_idx = text.index(_TEMPLATE_END)
|
||||
return text[start_idx:end_idx].strip() or None
|
||||
|
||||
|
||||
# ── LLM call ─────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
async def _call_llm(system_prompt: str, history: list[dict[str, Any]]) -> str:
|
||||
"""Build LangChain messages from history and invoke the LLM."""
|
||||
messages: list[Any] = [SystemMessage(content=system_prompt)]
|
||||
for turn in history:
|
||||
if turn["role"] == "user":
|
||||
messages.append(HumanMessage(content=turn["content"]))
|
||||
else:
|
||||
messages.append(AIMessage(content=turn["content"]))
|
||||
|
||||
llm = get_llm(model=None, temperature=0.4)
|
||||
response = await llm.ainvoke(messages)
|
||||
return response.content # type: ignore[return-value]
|
||||
|
||||
|
||||
# ── Existing-config loader ────────────────────────────────────────────────
|
||||
|
||||
|
||||
async def _load_existing_template(
|
||||
agent_id: str,
|
||||
user_id: str,
|
||||
db: AsyncSession,
|
||||
) -> str | None:
|
||||
"""Return the prompt_template of an existing agent config, or None."""
|
||||
# Try local first, then cloud.
|
||||
local_result = await db.execute(
|
||||
select(LocalAgentConfig).where(
|
||||
LocalAgentConfig.id == agent_id,
|
||||
LocalAgentConfig.user_id == user_id,
|
||||
)
|
||||
)
|
||||
local = local_result.scalar_one_or_none()
|
||||
if local is not None:
|
||||
return local.prompt_template
|
||||
|
||||
cloud_result = await db.execute(
|
||||
select(CloudAgentConfig).where(
|
||||
CloudAgentConfig.id == agent_id,
|
||||
CloudAgentConfig.user_id == user_id,
|
||||
)
|
||||
)
|
||||
cloud = cloud_result.scalar_one_or_none()
|
||||
return cloud.prompt_template if cloud is not None else None
|
||||
|
||||
|
||||
# ── Routes ────────────────────────────────────────────────────────────────
|
||||
|
||||
|
||||
@router.post("/start", response_model=JourneyResponse, status_code=status.HTTP_200_OK)
|
||||
async def start_journey(
|
||||
body: JourneyStartRequest,
|
||||
current_user: UserProfile = Depends(get_current_user),
|
||||
db: AsyncSession = Depends(get_session),
|
||||
) -> JourneyResponse:
|
||||
"""Start a new Chatbot Journey session.
|
||||
|
||||
If ``agent_id`` is provided the session is pre-seeded with the existing
|
||||
agent's ``prompt_template`` so the user can refine it.
|
||||
"""
|
||||
# Load existing template (may be None).
|
||||
existing_template: str | None = None
|
||||
if body.agent_id:
|
||||
existing_template = await _load_existing_template(body.agent_id, current_user.id, db)
|
||||
# If agent_id was given but not found, proceed without seeding (don't 404 —
|
||||
# the user may be starting a fresh journey for a not-yet-persisted config).
|
||||
|
||||
system_prompt = _build_system_prompt(body.agent_type, existing_template)
|
||||
first_question = _first_question(body.agent_type)
|
||||
|
||||
session_id = str(uuid.uuid4())
|
||||
session = _JourneySession(
|
||||
session_id=session_id,
|
||||
user_id=current_user.id,
|
||||
agent_type=body.agent_type,
|
||||
# Seed history with the AI's first question so it stays consistent.
|
||||
history=[{"role": "assistant", "content": first_question}],
|
||||
)
|
||||
# Store the system prompt inside the session for reuse in /message.
|
||||
session.__dict__["_system_prompt"] = system_prompt # type: ignore[index]
|
||||
_sessions[session_id] = session
|
||||
|
||||
logger.info("Journey session %s started for user %s (agent_type=%s)", session_id, current_user.id, body.agent_type)
|
||||
return JourneyResponse(session_id=session_id, message=first_question, done=False)
|
||||
|
||||
|
||||
@router.post("/message", response_model=JourneyResponse, status_code=status.HTTP_200_OK)
|
||||
async def send_journey_message(
|
||||
body: JourneyMessageRequest,
|
||||
current_user: UserProfile = Depends(get_current_user),
|
||||
db: AsyncSession = Depends(get_session),
|
||||
) -> JourneyResponse:
|
||||
"""Send a message in an existing Chatbot Journey session.
|
||||
|
||||
The server appends the user's message to the conversation history,
|
||||
calls the LLM, and appends the AI reply. When the LLM wraps up with a
|
||||
``prompt_template`` block the response includes ``done=True`` and the
|
||||
extracted template.
|
||||
"""
|
||||
session = _get_session(body.session_id, current_user.id)
|
||||
system_prompt: str = session.__dict__.get("_system_prompt", _build_system_prompt(session.agent_type, None)) # type: ignore[assignment]
|
||||
|
||||
# Append user turn to history.
|
||||
session.history.append({"role": "user", "content": body.message})
|
||||
|
||||
# Call the LLM with the full conversation so far.
|
||||
ai_reply = await _call_llm(system_prompt, session.history)
|
||||
|
||||
# Append AI turn.
|
||||
session.history.append({"role": "assistant", "content": ai_reply})
|
||||
|
||||
# Check if the LLM produced the final template.
|
||||
prompt_template = _extract_template(ai_reply)
|
||||
done = prompt_template is not None
|
||||
|
||||
# Strip the sentinel markers from the message shown to the user.
|
||||
display_message = ai_reply
|
||||
if done:
|
||||
display_message = (
|
||||
ai_reply[: ai_reply.index(_TEMPLATE_START)].strip()
|
||||
or "Here is your agent configuration. You can save it or continue refining."
|
||||
)
|
||||
|
||||
if done:
|
||||
logger.info("Journey session %s completed for user %s", body.session_id, current_user.id)
|
||||
# Clean up the session immediately on completion.
|
||||
_sessions.pop(body.session_id, None)
|
||||
else:
|
||||
# Nudge the LLM to wrap up after max turns.
|
||||
turns = sum(1 for t in session.history if t["role"] == "user")
|
||||
if turns >= _MAX_TURNS:
|
||||
# Add a system-level nudge as a hidden user message.
|
||||
session.history.append({
|
||||
"role": "user",
|
||||
"content": (
|
||||
"[System: You have enough information. Please generate the final "
|
||||
f"prompt_template now, wrapped in {_TEMPLATE_START} / {_TEMPLATE_END} markers.]"
|
||||
),
|
||||
})
|
||||
|
||||
return JourneyResponse(
|
||||
session_id=body.session_id,
|
||||
message=display_message,
|
||||
done=done,
|
||||
prompt_template=prompt_template,
|
||||
)
|
||||
Reference in New Issue
Block a user