Log client details for API and agent requests

.env.example

@@ -23,4 +23,4 @@ VAPID_PUBLIC_KEY=
 
 # ── AI agent (optional in dev; Asistente won't work without it) ──────────────
 OPENAI_API_KEY=
-AGENT_MODEL=gpt-5.4-mini
+AGENT_MODEL=gpt-5.6-luna

.github/workflows/deploy.yml

@@ -51,7 +51,7 @@ jobs:
           VAPID_PRIVATE_KEY=${{ secrets.VAPID_PRIVATE_KEY }}
           VAPID_PUBLIC_KEY=${{ secrets.VAPID_PUBLIC_KEY }}
           OPENAI_API_KEY=${{ secrets.OPENAI_API_KEY }}
-          AGENT_MODEL=gpt-5.4-mini
+          AGENT_MODEL=${{ secrets.AGENT_MODEL }}
           ENVEOF
           sed -i 's/^[[:space:]]*//' .env.prod
 

.gitignore

@@ -16,3 +16,8 @@ tech_docs/
 .claude/
 .venv/
 frontend/openapi.json
+
+# playwright (demo artifacts are generated, not committed)
+frontend/test-results/
+frontend/playwright-report/
+frontend/e2e-docs/

backend/alembic/versions/10f4a4f71964_track_agui_run_id_in_chat_logs.py

@@ -0,0 +1,35 @@
+"""track agui run id in chat logs
+
+Revision ID: 10f4a4f71964
+Revises: ecb99a158fbf
+Create Date: 2026-07-14 22:32:16.771655
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel
+
+
+# revision identifiers, used by Alembic.
+revision: str = '10f4a4f71964'
+down_revision: Union[str, Sequence[str], None] = 'ecb99a158fbf'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('chatrunlog', sa.Column('agui_run_id', sqlmodel.sql.sqltypes.AutoString(), nullable=True))
+    op.create_index(op.f('ix_chatrunlog_agui_run_id'), 'chatrunlog', ['agui_run_id'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_chatrunlog_agui_run_id'), table_name='chatrunlog')
+    op.drop_column('chatrunlog', 'agui_run_id')
+    # ### end Alembic commands ###

backend/alembic/versions/86104b4ff6ae_record_chat_client_details.py

@@ -0,0 +1,37 @@
+"""record chat client details
+
+Revision ID: 86104b4ff6ae
+Revises: 10f4a4f71964
+Create Date: 2026-07-14 22:54:55.519380
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel
+
+
+# revision identifiers, used by Alembic.
+revision: str = '86104b4ff6ae'
+down_revision: Union[str, Sequence[str], None] = '10f4a4f71964'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('chatrunlog', sa.Column('client_ip', sa.Text(), nullable=True))
+    op.add_column('chatrunlog', sa.Column('user_agent', sa.Text(), nullable=True))
+    op.add_column('chatrunlog', sa.Column('browser', sa.Text(), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('chatrunlog', 'browser')
+    op.drop_column('chatrunlog', 'user_agent')
+    op.drop_column('chatrunlog', 'client_ip')
+    # ### end Alembic commands ###

backend/alembic/versions/ecb99a158fbf_add_chat_run_audit_logs.py

@@ -0,0 +1,58 @@
+"""add chat run audit logs
+
+Revision ID: ecb99a158fbf
+Revises: 794baf50635b
+Create Date: 2026-07-14 22:22:06.035643
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = 'ecb99a158fbf'
+down_revision: Union[str, Sequence[str], None] = '794baf50635b'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('chatrunlog',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('request_id', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+    sa.Column('requested_thread_id', sqlmodel.sql.sqltypes.AutoString(), nullable=True),
+    sa.Column('response_thread_id', sqlmodel.sql.sqltypes.AutoString(), nullable=True),
+    sa.Column('model', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+    sa.Column('user_prompt', sa.Text(), nullable=True),
+    sa.Column('tool_calls', sa.JSON().with_variant(postgresql.JSONB(astext_type=sa.Text()), 'postgresql'), server_default='[]', nullable=False),
+    sa.Column('assistant_response', sa.Text(), nullable=True),
+    sa.Column('status', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+    sa.Column('error', sa.Text(), nullable=True),
+    sa.Column('started_at', sa.DateTime(), nullable=False),
+    sa.Column('completed_at', sa.DateTime(), nullable=True),
+    sa.Column('expires_at', sa.DateTime(), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_index(op.f('ix_chatrunlog_expires_at'), 'chatrunlog', ['expires_at'], unique=False)
+    op.create_index(op.f('ix_chatrunlog_request_id'), 'chatrunlog', ['request_id'], unique=True)
+    op.create_index(op.f('ix_chatrunlog_requested_thread_id'), 'chatrunlog', ['requested_thread_id'], unique=False)
+    op.create_index(op.f('ix_chatrunlog_response_thread_id'), 'chatrunlog', ['response_thread_id'], unique=False)
+    op.create_index(op.f('ix_chatrunlog_status'), 'chatrunlog', ['status'], unique=False)
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_index(op.f('ix_chatrunlog_status'), table_name='chatrunlog')
+    op.drop_index(op.f('ix_chatrunlog_response_thread_id'), table_name='chatrunlog')
+    op.drop_index(op.f('ix_chatrunlog_requested_thread_id'), table_name='chatrunlog')
+    op.drop_index(op.f('ix_chatrunlog_request_id'), table_name='chatrunlog')
+    op.drop_index(op.f('ix_chatrunlog_expires_at'), table_name='chatrunlog')
+    op.drop_table('chatrunlog')
+    # ### end Alembic commands ###

backend/app/agent/agent.py

@@ -3,7 +3,7 @@
 from __future__ import annotations
 
 from agent_framework import Agent
-from agent_framework.openai import OpenAIChatCompletionClient
+from agent_framework.openai import OpenAIChatClient
 
 from app.config import settings
 from app.agent.tools import TOOLS
@@ -35,6 +35,9 @@ How to answer:
   "ayer", "el martes", a specific date) need get_daily_spending with that
   day's bounds — cycle or category summaries have NO per-day data, so never
   answer a day question from them.
+- For a question about a specific salary deposit or its amount (including
+  "cuánto recibí hoy"), call get_salary_deposits with the relevant date range;
+  get_salary_summary is aggregate-only and cannot answer it.
 - Answer like an analyst, not a calculator. An aggregate number on its own
   is not an answer — show what it is made of, right away, without waiting
   to be asked:
@@ -83,7 +86,9 @@ Generative UI — render tools:
 
 
 def build_agent() -> Agent:
-    client = OpenAIChatCompletionClient(
+    # Use the Responses API for every configured model. It preserves one tool
+    # transport across model changes and supports Luna's tool-result turns.
+    client = OpenAIChatClient(
         api_key=settings.OPENAI_API_KEY,
         model=settings.AGENT_MODEL,
     )

backend/app/agent/chat_audit.py

@@ -0,0 +1,153 @@
+"""Durable diagnostics for individual AG-UI agent runs."""
+
+from __future__ import annotations
+
+import asyncio
+import contextvars
+from datetime import timedelta
+from typing import Any
+
+from sqlmodel import Session, delete, select
+
+from app.config import settings
+from app.db import engine
+from app.models.models import ChatRunLog
+from app.timeutil import utcnow
+
+
+CHAT_LOG_RETENTION_DAYS = 90
+_chat_run_id: contextvars.ContextVar[int | None] = contextvars.ContextVar(
+    "chat_run_id", default=None
+)
+
+
+def set_current_chat_run(run_id: int) -> contextvars.Token:
+    return _chat_run_id.set(run_id)
+
+
+def reset_current_chat_run(token: contextvars.Token) -> None:
+    _chat_run_id.reset(token)
+
+
+def current_chat_run_id() -> int | None:
+    return _chat_run_id.get()
+
+
+def _last_user_prompt(messages: list[dict[str, Any]]) -> str | None:
+    for message in reversed(messages):
+        if message.get("role") == "user" and isinstance(message.get("content"), str):
+            return message["content"]
+    return None
+
+
+def create_chat_run(
+    *,
+    request_id: str,
+    agui_run_id: str | None,
+    thread_id: str | None,
+    messages: list[dict[str, Any]],
+    client_ip: str | None = None,
+    user_agent: str | None = None,
+    browser: str | None = None,
+) -> int:
+    now = utcnow()
+    with Session(engine) as session:
+        row = ChatRunLog(
+            request_id=request_id,
+            agui_run_id=agui_run_id,
+            requested_thread_id=thread_id,
+            model=settings.AGENT_MODEL,
+            client_ip=client_ip,
+            user_agent=user_agent,
+            browser=browser,
+            user_prompt=_last_user_prompt(messages),
+            expires_at=now + timedelta(days=CHAT_LOG_RETENTION_DAYS),
+        )
+        session.add(row)
+        session.commit()
+        session.refresh(row)
+        assert row.id is not None
+        return row.id
+
+
+def _tool_activity(messages: list[dict[str, Any]]) -> list[dict[str, Any]]:
+    calls: dict[str, dict[str, Any]] = {}
+    order: list[str] = []
+    for message in messages:
+        if message.get("role") == "assistant":
+            for call in message.get("toolCalls") or message.get("tool_calls") or []:
+                call_id = str(call.get("id") or "")
+                if not call_id or call_id in calls:
+                    continue
+                function = call.get("function") or {}
+                calls[call_id] = {
+                    "id": call_id,
+                    "name": function.get("name"),
+                    "arguments": function.get("arguments"),
+                }
+                order.append(call_id)
+        elif message.get("role") == "tool":
+            call_id = str(message.get("toolCallId") or message.get("tool_call_id") or "")
+            if call_id in calls:
+                calls[call_id]["result"] = message.get("content")
+                if message.get("error") is not None:
+                    calls[call_id]["error"] = message["error"]
+    return [calls[call_id] for call_id in order]
+
+
+def _last_assistant_response(messages: list[dict[str, Any]]) -> str | None:
+    for message in reversed(messages):
+        if message.get("role") == "assistant" and isinstance(message.get("content"), str):
+            return message["content"]
+    return None
+
+
+def finalize_chat_run_in_session(
+    session: Session, *, run_id: int, response_thread_id: str, messages: list[dict[str, Any]]
+) -> None:
+    row = session.get(ChatRunLog, run_id)
+    if row is None:
+        return
+    row.response_thread_id = response_thread_id
+    row.tool_calls = _tool_activity(messages)
+    row.assistant_response = _last_assistant_response(messages)
+    row.status = "completed"
+    row.completed_at = utcnow()
+    session.add(row)
+
+
+def mark_chat_run_failed(run_id: int, error: str) -> None:
+    with Session(engine) as session:
+        row = session.get(ChatRunLog, run_id)
+        if row is None or row.status == "completed":
+            return
+        row.status = "failed"
+        row.error = error[:4000]
+        row.completed_at = utcnow()
+        session.add(row)
+        session.commit()
+
+
+def finish_pending_chat_run(run_id: int) -> None:
+    with Session(engine) as session:
+        row = session.get(ChatRunLog, run_id)
+        if row is None or row.status != "started":
+            return
+        row.status = "completed"
+        row.completed_at = utcnow()
+        session.add(row)
+        session.commit()
+
+
+def purge_expired_chat_runs() -> int:
+    with Session(engine) as session:
+        result = session.exec(delete(ChatRunLog).where(ChatRunLog.expires_at < utcnow()))
+        session.commit()
+        return result.rowcount or 0
+
+
+async def purge_expired_chat_runs_periodically() -> None:
+    """Purge at startup and then once per day for a bounded audit footprint."""
+    while True:
+        await asyncio.to_thread(purge_expired_chat_runs)
+        await asyncio.sleep(24 * 60 * 60)

backend/app/agent/snapshot_store.py

@@ -25,6 +25,7 @@ from agent_framework_ag_ui import AGUIThreadSnapshot
 from sqlmodel import Session, select
 
 from app.db import engine
+from app.agent.chat_audit import current_chat_run_id, finalize_chat_run_in_session
 from app.models.models import ChatThreadSnapshot
 from app.timeutil import utcnow
 
@@ -130,6 +131,14 @@ class PostgresSnapshotStore:
                 row.interrupt = snapshot.interrupt
                 row.updated_at = utcnow()
                 session.add(row)
+                run_id = current_chat_run_id()
+                if run_id is not None:
+                    finalize_chat_run_in_session(
+                        session,
+                        run_id=run_id,
+                        response_thread_id=thread_id,
+                        messages=row.messages,
+                    )
                 session.commit()
 
         await asyncio.to_thread(_save)

backend/app/agent/tools.py

@@ -48,6 +48,7 @@ from app.services.exchange_rate import (
 )
 
 _session_ctx: contextvars.ContextVar[Session] = contextvars.ContextVar("agent_session")
+SALARY_TRANSACTION_TYPES = (TransactionType.SALARY, TransactionType.DEPOSITO)
 
 
 def set_session(session: Session) -> contextvars.Token:
@@ -339,7 +340,7 @@ def get_salary_summary() -> dict:
             func.count(),
             func.coalesce(func.sum(amount_crc), 0),
             func.max(Transaction.date),
-        ).where(Transaction.transaction_type == TransactionType.SALARY)
+        ).where(col(Transaction.transaction_type).in_(SALARY_TRANSACTION_TYPES))
     ).first()
     count = row[0] if row else 0
     total = float(row[1]) if row else 0.0
@@ -347,6 +348,44 @@ def get_salary_summary() -> dict:
     return {"count": count, "total_crc": total, "latest_date": latest}
 
 
+def get_salary_deposits(
+    limit: Annotated[int, Field(ge=1, le=100, description="How many deposits to return")] = 20,
+    start_date: Annotated[
+        Optional[str], Field(description="ISO date lower bound, inclusive")
+    ] = None,
+    end_date: Annotated[
+        Optional[str], Field(description="ISO date upper bound, exclusive")
+    ] = None,
+) -> list[dict]:
+    """Individual salary deposits, newest first. Use this for questions about
+    a specific salary or a day/range (for example, "cuánto recibí hoy").
+    Amounts remain in their recorded currency; use the currency field when
+    presenting them."""
+    q = select(Transaction).where(
+        col(Transaction.transaction_type).in_(SALARY_TRANSACTION_TYPES)
+    )
+    if start_date:
+        q = q.where(Transaction.date >= datetime.fromisoformat(start_date))
+    if end_date:
+        q = q.where(Transaction.date < datetime.fromisoformat(end_date))
+    q = q.order_by(col(Transaction.date).desc(), col(Transaction.id).desc()).limit(limit)
+    return [
+        {
+            "id": t.id,
+            "date": t.date.isoformat(),
+            "amount": float(t.amount),
+            "currency": t.currency.value,
+            "merchant": t.merchant,
+            "source": t.source.value,
+            "bank": t.bank.value,
+            "transaction_type": t.transaction_type.value,
+            "reference": t.reference,
+            "notes": t.notes,
+        }
+        for t in _s().exec(q).all()
+    ]
+
+
 def get_municipal_receipts(
     limit: Annotated[int, Field(ge=1, le=50)] = 12,
     offset: Annotated[int, Field(ge=0, description="Skip the N most recent")] = 0,
@@ -567,6 +606,7 @@ TOOLS = [
     list_recurring_items,
     get_pension_snapshots,
     get_salary_summary,
+    get_salary_deposits,
     get_municipal_receipts,
     get_analytics_by_category,
     get_monthly_trend,

backend/app/config.py

@@ -20,7 +20,7 @@ class Settings(BaseSettings):
     VAPID_PUBLIC_KEY: str = ""
     VAPID_CLAIM_EMAIL: str = "mailto:admin@wealth.cescalante.dev"
     OPENAI_API_KEY: str = ""
-    AGENT_MODEL: str = "gpt-5.4-mini"
+    AGENT_MODEL: str = "gpt-5.6-luna"
 
     @property
     def cors_origins_list(self) -> list[str]:

backend/app/logging.py

@@ -0,0 +1,31 @@
+"""Structured, redacted application logging for container stdout."""
+
+from __future__ import annotations
+
+import json
+from datetime import date, datetime
+from enum import Enum
+from typing import Any
+
+
+class _JSONEncoder(json.JSONEncoder):
+    def default(self, value: Any) -> Any:
+        if isinstance(value, (datetime, date)):
+            return value.isoformat()
+        if isinstance(value, Enum):
+            return value.value
+        return super().default(value)
+
+
+def configure_structured_logging() -> None:
+    """Reserved lifecycle hook for the structured stdout audit channel."""
+
+
+def log_event(event: str, **fields: Any) -> None:
+    """Write a single JSON line; callers must not pass credentials or bodies."""
+    # stdout is Docker's durable capture point. `flush=True` also makes this
+    # visible immediately in `docker compose logs` during an active SSE run.
+    print(
+        json.dumps({"event": event, **fields}, cls=_JSONEncoder, separators=(",", ":")),
+        flush=True,
+    )

backend/app/main.py

@@ -1,6 +1,7 @@
 import asyncio
 import json
 import uuid
+from time import perf_counter
 from http.cookies import SimpleCookie
 from contextlib import asynccontextmanager
 
@@ -11,6 +12,14 @@ from jose import JWTError, jwt
 from pydantic import BaseModel
 
 from app.agent.agent import build_agent
+from app.agent.chat_audit import (
+    create_chat_run,
+    finish_pending_chat_run,
+    mark_chat_run_failed,
+    purge_expired_chat_runs_periodically,
+    reset_current_chat_run,
+    set_current_chat_run,
+)
 from app.agent.snapshot_store import PostgresSnapshotStore
 from app.agent.tools import reset_session, set_session
 from app.api.v1.router import api_router
@@ -25,9 +34,45 @@ from app.db import get_session, run_alembic_upgrade
 from app.seed import seed_db
 from app.timeutil import reset_client_timezone, set_client_timezone
 from app.services.exchange_rate import refresh_rates_periodically
+from app.logging import configure_structured_logging, log_event
 
 
 AGENT_PATH = "/api/v1/agent/agui"
+MAX_USER_AGENT_LENGTH = 512
+
+
+def _request_client_details(request: Request) -> tuple[str, str | None, str | None]:
+    """Return the browser client details propagated through the frontend BFF.
+
+    Production nginx-proxy supplies X-Real-IP and the frontend forwards it to
+    FastAPI. For direct local development, fall back to X-Forwarded-For and
+    then the socket peer. The BFF is the only production path to the backend,
+    which is not publicly exposed.
+    """
+    client_ip = request.headers.get("x-real-ip", "").strip()
+    if not client_ip:
+        forwarded = request.headers.get("x-forwarded-for", "")
+        client_ip = forwarded.split(",", 1)[0].strip()
+    if not client_ip:
+        client_ip = request.client.host if request.client else "unknown"
+
+    user_agent = request.headers.get("user-agent", "").strip()[:MAX_USER_AGENT_LENGTH] or None
+    if not user_agent:
+        return client_ip, None, None
+    ua = user_agent.lower()
+    if "edg/" in ua or "edgios/" in ua:
+        browser = "Edge"
+    elif "opr/" in ua or "opera" in ua:
+        browser = "Opera"
+    elif "firefox/" in ua or "fxios/" in ua:
+        browser = "Firefox"
+    elif "chrome/" in ua or "crios/" in ua:
+        browser = "Chrome"
+    elif "safari/" in ua:
+        browser = "Safari"
+    else:
+        browser = "Other"
+    return client_ip, user_agent, browser
 
 
 def _pair_orphan_tool_calls(messages: list) -> list:
@@ -101,17 +146,24 @@ def _drop_stale_client_history(session, thread_id, messages: list) -> list:
 
 @asynccontextmanager
 async def lifespan(app: FastAPI):
+    configure_structured_logging()
     run_alembic_upgrade()
     seed_db()
     rate_refresh_task = asyncio.create_task(refresh_rates_periodically())
+    chat_audit_cleanup_task = asyncio.create_task(purge_expired_chat_runs_periodically())
     try:
         yield
     finally:
         rate_refresh_task.cancel()
+        chat_audit_cleanup_task.cancel()
         try:
             await rate_refresh_task
         except asyncio.CancelledError:
             pass
+        try:
+            await chat_audit_cleanup_task
+        except asyncio.CancelledError:
+            pass
 
 
 app = FastAPI(title="WealthySmart API", version="0.1.0", lifespan=lifespan)
@@ -125,6 +177,67 @@ app.add_middleware(
 )
 
 
+async def log_api_request(request: Request, call_next):
+    """Emit redacted, one-line diagnostics for API requests only.
+
+    This deliberately records no request/response bodies, headers, tokens,
+    passwords, or financial payloads. Full assistant content is retained only
+    in the bounded chat-run audit table.
+    """
+    request_id = uuid.uuid4().hex
+    request.state.request_id = request_id
+    client_ip, user_agent, browser = _request_client_details(request)
+    request.state.client_ip = client_ip
+    request.state.user_agent = user_agent
+    request.state.browser = browser
+    started = perf_counter()
+    status_code = 500
+    is_logged_api = request.url.path.startswith("/api/") and request.url.path != "/api/health"
+
+    def emit(error_type: str | None = None) -> None:
+        if not is_logged_api:
+            return
+        route = request.scope.get("route")
+        log_event(
+            "api_request",
+            request_id=request_id,
+            method=request.method,
+            path=getattr(route, "path", request.url.path),
+            status_code=status_code,
+            duration_ms=round((perf_counter() - started) * 1000, 1),
+            error_type=error_type,
+            client_ip=client_ip,
+            user_agent=user_agent,
+            browser=browser,
+        )
+
+    try:
+        response = await call_next(request)
+        status_code = response.status_code
+        response.headers["X-Request-ID"] = request_id
+        original_iterator = getattr(response, "body_iterator", None)
+        if original_iterator is None:
+            emit()
+            return response
+
+        async def logged_stream():
+            error_type: str | None = None
+            try:
+                async for chunk in original_iterator:
+                    yield chunk
+            except Exception as exc:
+                error_type = type(exc).__name__
+                raise
+            finally:
+                emit(error_type)
+
+        response.body_iterator = logged_stream()
+        return response
+    except Exception as exc:
+        emit(type(exc).__name__)
+        raise
+
+
 @app.middleware("http")
 async def agent_auth_and_session(request: Request, call_next):
     """For the AG-UI route, validate the JWT, repair message history, and
@@ -159,6 +272,7 @@ async def agent_auth_and_session(request: Request, call_next):
     session = next(session_gen)
     token_var = set_session(session)
 
+    chat_run_id: int | None = None
     # Repair orphan tool_calls before the MAF agent sees the message history.
     if request.method == "POST" and "application/json" in request.headers.get("content-type", ""):
         raw = await request.body()
@@ -172,16 +286,75 @@ async def agent_auth_and_session(request: Request, call_next):
                 )
                 body["messages"] = _pair_orphan_tool_calls(body["messages"])
                 raw = json.dumps(body).encode()
-        except Exception:
+            log_event(
-            pass
+                "agent_request",
+                request_id=request.state.request_id,
+                agui_run_id=body.get("runId"),
+                thread_id=body.get("threadId") or body.get("thread_id"),
+                message_count=len(body.get("messages") or []),
+                has_user_message=any(
+                    message.get("role") == "user" for message in body.get("messages") or []
+                ),
+                client_ip=request.state.client_ip,
+                user_agent=request.state.user_agent,
+                browser=request.state.browser,
+            )
+            # The BFF removes its `method: agent/run` envelope before
+            # forwarding to MAF. A non-empty user message is the reliable
+            # backend-side distinction between an agent run and hydration.
+            if any(message.get("role") == "user" for message in body.get("messages") or []):
+                chat_run_id = create_chat_run(
+                    request_id=request.state.request_id,
+                    agui_run_id=body.get("runId"),
+                    thread_id=body.get("threadId") or body.get("thread_id"),
+                    messages=body.get("messages") or [],
+                    client_ip=request.state.client_ip,
+                    user_agent=request.state.user_agent,
+                    browser=request.state.browser,
+                )
+        except Exception as exc:
+            # Parsing/repair must not prevent the agent endpoint from serving;
+            # the access log will still capture a resulting error response.
+            log_event(
+                "chat_audit_start_failed",
+                request_id=request.state.request_id,
+                error_type=type(exc).__name__,
+            )
+            body = None
         # Starlette caches the body; replace it so call_next sees the fixed bytes.
         request._body = raw  # type: ignore[attr-defined]
     # Browser's IANA timezone, forwarded by the BFF — lets tools resolve
     # "today" wherever the user is (falls back to Costa Rica).
     tz_token = set_client_timezone(request.headers.get("x-client-timezone"))
+    audit_token = set_current_chat_run(chat_run_id) if chat_run_id is not None else None
     try:
-        return await call_next(request)
+        response = await call_next(request)
+        if chat_run_id is None:
+            return response
+
+        original_iterator = response.body_iterator
+
+        async def audit_stream():
+            try:
+                async for chunk in original_iterator:
+                    yield chunk
+            except Exception as exc:
+                mark_chat_run_failed(chat_run_id, f"{type(exc).__name__}: {exc}")
+                raise
+            else:
+                # MAF normally finalizes via PostgresSnapshotStore.save(). If
+                # it emitted no snapshot, do not leave a permanently-open row.
+                finish_pending_chat_run(chat_run_id)
+
+        response.body_iterator = audit_stream()
+        return response
+    except Exception as exc:
+        if chat_run_id is not None:
+            mark_chat_run_failed(chat_run_id, f"{type(exc).__name__}: {exc}")
+        raise
     finally:
+        if audit_token is not None:
+            reset_current_chat_run(audit_token)
         reset_client_timezone(tz_token)
         reset_session(token_var)
         try:
@@ -190,6 +363,12 @@ async def agent_auth_and_session(request: Request, call_next):
             pass
 
 
+# FastAPI wraps function middlewares in reverse registration order. Register
+# this after the AG-UI auth middleware so it observes every API response,
+# including auth failures that return before calling the inner application.
+app.middleware("http")(log_api_request)
+
+
 # Register app routes
 app.include_router(api_router)
 

backend/app/models/models.py

@@ -4,7 +4,7 @@ from decimal import Decimal
 from typing import Annotated, Optional
 
 from pydantic import PlainSerializer
-from sqlalchemy import JSON, Column, UniqueConstraint
+from sqlalchemy import JSON, Column, Text, UniqueConstraint
 from sqlalchemy.dialects.postgresql import JSONB
 from sqlmodel import Field, Relationship, SQLModel
 
@@ -566,3 +566,38 @@ class ChatThreadSnapshot(SQLModel, table=True):
         default=None, sa_column=Column(JSON_OR_JSONB, nullable=True)
     )
     updated_at: datetime = Field(default_factory=utcnow)
+
+
+# --- Assistant Chat Run Audit ---
+
+
+class ChatRunLog(SQLModel, table=True):
+    """Append-only diagnostic record for an AG-UI agent/run request.
+
+    Thread snapshots are mutable conversation state. This table instead keeps
+    the request, model, tool activity, and final emitted answer for a bounded
+    retention period so individual assistant runs can be investigated later.
+    """
+
+    id: Optional[int] = Field(default=None, primary_key=True)
+    request_id: str = Field(index=True, unique=True)
+    agui_run_id: Optional[str] = Field(default=None, index=True)
+    requested_thread_id: Optional[str] = Field(default=None, index=True)
+    response_thread_id: Optional[str] = Field(default=None, index=True)
+    model: str
+    client_ip: Optional[str] = Field(default=None, sa_column=Column(Text, nullable=True))
+    user_agent: Optional[str] = Field(default=None, sa_column=Column(Text, nullable=True))
+    browser: Optional[str] = Field(default=None, sa_column=Column(Text, nullable=True))
+    user_prompt: Optional[str] = Field(default=None, sa_column=Column(Text, nullable=True))
+    tool_calls: list = Field(
+        default_factory=list,
+        sa_column=Column(JSON_OR_JSONB, nullable=False, server_default="[]"),
+    )
+    assistant_response: Optional[str] = Field(
+        default=None, sa_column=Column(Text, nullable=True)
+    )
+    status: str = Field(default="started", index=True)
+    error: Optional[str] = Field(default=None, sa_column=Column(Text, nullable=True))
+    started_at: datetime = Field(default_factory=utcnow)
+    completed_at: Optional[datetime] = Field(default=None)
+    expires_at: datetime = Field(index=True)

backend/constraints.txt

@@ -1,8 +1,8 @@
 a2a-sdk==0.3.23
 ag-ui-protocol==0.1.19
-agent-framework==1.10.0
+agent-framework==1.11.0
 agent-framework-a2a==1.0.0b260428
-agent-framework-ag-ui==1.0.0rc7
+agent-framework-ag-ui==1.0.0rc8
 agent-framework-anthropic==1.0.0b260428
 agent-framework-azure-ai-search==1.0.0b260428
 agent-framework-azure-cosmos==1.0.0b260428
@@ -11,7 +11,7 @@ agent-framework-bedrock==1.0.0b260428
 agent-framework-chatkit==1.0.0b260428
 agent-framework-claude==1.0.0b260428
 agent-framework-copilotstudio==1.0.0b260428
-agent-framework-core==1.10.0
+agent-framework-core==1.11.0
 agent-framework-declarative==1.0.0b260428
 agent-framework-devui==1.0.0b260428
 agent-framework-durabletask==1.0.0b260428
@@ -21,7 +21,7 @@ agent-framework-github-copilot==1.0.0b260402
 agent-framework-lab==1.0.0b251024
 agent-framework-mem0==1.0.0b260428
 agent-framework-ollama==1.0.0b260428
-agent-framework-openai==1.10.0
+agent-framework-openai==1.10.1
 agent-framework-orchestrations==1.0.0b260428
 agent-framework-purview==1.0.0b260428
 agent-framework-redis==1.0.0b260428
@@ -165,7 +165,7 @@ six==1.17.0
 sniffio==1.3.1
 SQLAlchemy==2.0.50
 sqlmodel==0.0.38
-sse-starlette==3.4.4
+sse-starlette==3.4.5
 starlette==1.2.1
 tenacity==9.1.4
 tqdm==4.68.2

backend/requirements.txt

@@ -11,6 +11,6 @@ httpx
 pywebpush
 py-vapid
 python-dateutil
-agent-framework==1.10.0
+agent-framework==1.11.0
-agent-framework-ag-ui==1.0.0rc7
+agent-framework-ag-ui==1.0.0rc8
-agent-framework-openai==1.10.0
+agent-framework-openai==1.10.1

backend/tests/test_agent_config.py

@@ -0,0 +1,14 @@
+"""Assistant transport configuration."""
+
+from agent_framework.openai import OpenAIChatClient
+
+from app.agent import agent as agent_module
+
+
+def test_agent_uses_responses_client_for_the_configured_model(monkeypatch):
+    monkeypatch.setattr(agent_module.settings, "AGENT_MODEL", "gpt-5.6-luna")
+
+    agent = agent_module.build_agent()
+
+    assert isinstance(agent.client, OpenAIChatClient)
+    assert agent.client.model == "gpt-5.6-luna"

backend/tests/test_agent_tools.py

@@ -17,6 +17,7 @@ from app.models.models import (
     MunicipalReceipt,
     PensionSnapshot,
     Transaction,
+    TransactionType,
     WaterMeterReading,
 )
 
@@ -173,6 +174,52 @@ def test_recent_transactions_exclude_future_cuotas(bound_session):
     assert "FUTURE CUOTA:03/06" not in merchants
 
 
+def test_salary_deposits_returns_individual_filtered_rows(bound_session):
+    bound_session.add_all(
+        [
+            Transaction(
+                amount=Decimal("1500"),
+                merchant="SALARY JULY",
+                date=datetime(2026, 7, 14, 9),
+                transaction_type=TransactionType.SALARY,
+                reference="PAY-2026-07",
+            ),
+            Transaction(
+                amount=Decimal("1400"),
+                merchant="SALARY JUNE",
+                date=datetime(2026, 6, 14, 9),
+                transaction_type=TransactionType.SALARY,
+            ),
+            Transaction(
+                amount=Decimal("999"),
+                merchant="PURCHASE",
+                date=datetime(2026, 7, 14, 10),
+            ),
+        ]
+    )
+    bound_session.commit()
+
+    out = tools.get_salary_deposits(
+        start_date="2026-07-14", end_date="2026-07-15"
+    )
+
+    json.dumps(out)
+    assert out == [
+        {
+            "id": out[0]["id"],
+            "date": "2026-07-14T09:00:00",
+            "amount": 1500.0,
+            "currency": "CRC",
+            "merchant": "SALARY JULY",
+            "source": "CREDIT_CARD",
+            "bank": "BAC",
+            "transaction_type": "SALARY",
+            "reference": "PAY-2026-07",
+            "notes": None,
+        }
+    ]
+
+
 def test_get_current_date_is_costa_rica_and_cycle_consistent():
     from app.timeutil import today_cr
 

backend/tests/test_chat_audit.py

@@ -0,0 +1,139 @@
+"""Chat-run audit persistence and redacted HTTP access logs."""
+
+import asyncio
+from datetime import timedelta
+
+from agent_framework_ag_ui import AGUIThreadSnapshot
+from starlette.requests import Request
+from starlette.responses import Response
+from sqlmodel import select
+
+import app.agent.chat_audit as chat_audit
+import app.agent.snapshot_store as snapshot_store_module
+from app.agent.snapshot_store import PostgresSnapshotStore
+from app.models.models import ChatRunLog
+from app.timeutil import utcnow
+
+
+def _audit_store(monkeypatch, engine):
+    monkeypatch.setattr(chat_audit, "engine", engine)
+    monkeypatch.setattr(snapshot_store_module, "engine", engine)
+    return PostgresSnapshotStore()
+
+
+def test_snapshot_completes_chat_run_with_tools_and_response(monkeypatch, engine, session):
+    store = _audit_store(monkeypatch, engine)
+    run_id = chat_audit.create_chat_run(
+        request_id="req-1",
+        agui_run_id="run-1",
+        thread_id="main",
+        messages=[{"role": "user", "content": "¿Cuál es mi saldo?"}],
+        client_ip="203.0.113.7",
+        user_agent="Mozilla/5.0 TestBrowser/1.0",
+        browser="TestBrowser",
+    )
+    token = chat_audit.set_current_chat_run(run_id)
+    try:
+        asyncio.run(
+            store.save(
+                scope="default",
+                thread_id="resp_123",
+                snapshot=AGUIThreadSnapshot(
+                    messages=[
+                        {"id": "u1", "role": "user", "content": "¿Cuál es mi saldo?"},
+                        {
+                            "id": "a1",
+                            "role": "assistant",
+                            "content": None,
+                            "tool_calls": [
+                                {
+                                    "id": "call-1",
+                                    "type": "function",
+                                    "function": {"name": "get_net_worth", "arguments": "{}"},
+                                }
+                            ],
+                        },
+                        {"id": "t1", "role": "tool", "tool_call_id": "call-1", "content": "{\"net_crc\": 1}"},
+                        {"id": "a2", "role": "assistant", "content": "Tu saldo es ₡1."},
+                    ]
+                ),
+            )
+        )
+    finally:
+        chat_audit.reset_current_chat_run(token)
+
+    row = session.get(ChatRunLog, run_id)
+    assert row is not None
+    assert row.status == "completed"
+    assert row.agui_run_id == "run-1"
+    assert row.response_thread_id == "resp_123"
+    assert row.user_prompt == "¿Cuál es mi saldo?"
+    assert row.client_ip == "203.0.113.7"
+    assert row.user_agent == "Mozilla/5.0 TestBrowser/1.0"
+    assert row.browser == "TestBrowser"
+    assert row.assistant_response == "Tu saldo es ₡1."
+    assert row.tool_calls == [
+        {
+            "id": "call-1",
+            "name": "get_net_worth",
+            "arguments": "{}",
+            "result": '{"net_crc": 1}',
+        }
+    ]
+
+
+def test_failure_and_retention_cleanup(monkeypatch, engine, session):
+    _audit_store(monkeypatch, engine)
+    failed_id = chat_audit.create_chat_run(
+        request_id="req-failed", agui_run_id="run-failed", thread_id="main", messages=[]
+    )
+    chat_audit.mark_chat_run_failed(failed_id, "RuntimeError: provider unavailable")
+    assert session.get(ChatRunLog, failed_id).status == "failed"
+
+    expired = ChatRunLog(
+        request_id="req-expired",
+        model="gpt-5.6-luna",
+        expires_at=utcnow() - timedelta(seconds=1),
+    )
+    session.add(expired)
+    session.commit()
+
+    assert chat_audit.purge_expired_chat_runs() == 1
+    assert session.exec(select(ChatRunLog).where(ChatRunLog.request_id == "req-expired")).first() is None
+
+
+def test_api_access_log_never_contains_request_body(monkeypatch):
+    from app.main import log_api_request
+
+    logged = []
+    monkeypatch.setattr("app.main.log_event", lambda event, **fields: logged.append((event, fields)))
+    scope = {
+        "type": "http",
+        "method": "POST",
+        "path": "/api/auth/login",
+        "raw_path": b"/api/auth/login",
+        "query_string": b"",
+        "headers": [
+            (b"x-real-ip", b"203.0.113.9"),
+            (b"user-agent", b"Mozilla/5.0 Chrome/138.0.0.0 Safari/537.36"),
+        ],
+        "scheme": "http",
+        "server": ("testserver", 80),
+        "client": ("testclient", 1234),
+    }
+    request = Request(scope)
+
+    async def call_next(_request):
+        return Response(status_code=201)
+
+    response = asyncio.run(log_api_request(request, call_next))
+    assert response.headers["X-Request-ID"]
+    assert logged[0][0] == "api_request"
+    fields = logged[0][1]
+    assert fields["path"] == "/api/auth/login"
+    assert fields["status_code"] == 201
+    assert fields["client_ip"] == "203.0.113.9"
+    assert fields["browser"] == "Chrome"
+    assert fields["user_agent"] == "Mozilla/5.0 Chrome/138.0.0.0 Safari/537.36"
+    assert "password" not in fields
+    assert "body" not in fields

docker-compose.prod.yml

@@ -16,6 +16,11 @@ services:
       interval: 10s
       timeout: 5s
       retries: 5
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "5"
 
   backend:
     build:
@@ -31,7 +36,7 @@ services:
       VAPID_PRIVATE_KEY: ${VAPID_PRIVATE_KEY}
       VAPID_PUBLIC_KEY: ${VAPID_PUBLIC_KEY}
       OPENAI_API_KEY: ${OPENAI_API_KEY}
-      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.4-mini}
+      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.6-luna}
       # MAF 1.6+ enables OTel instrumentation by default; keep it off explicitly.
       ENABLE_INSTRUMENTATION: "false"
     expose:
@@ -51,6 +56,11 @@ services:
       timeout: 5s
       retries: 3
       start_period: 10s
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "5"
 
   frontend:
     build:
@@ -84,6 +94,11 @@ services:
       interval: 30s
       timeout: 10s
       retries: 3
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "5"
 
 networks:
   wealthysmart-network:

docker-compose.yml

@@ -15,6 +15,11 @@ services:
       interval: 5s
       timeout: 3s
       retries: 5
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "5"
 
   backend:
     build:
@@ -30,7 +35,7 @@ services:
       VAPID_PRIVATE_KEY: ${VAPID_PRIVATE_KEY:-}
       VAPID_PUBLIC_KEY: ${VAPID_PUBLIC_KEY:-}
       OPENAI_API_KEY: ${OPENAI_API_KEY:-}
-      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.4-mini}
+      AGENT_MODEL: ${AGENT_MODEL:-gpt-5.6-luna}
       # MAF 1.6+ enables OTel instrumentation by default; keep it off explicitly.
       ENABLE_INSTRUMENTATION: "false"
     ports:
@@ -40,6 +45,11 @@ services:
     depends_on:
       db:
         condition: service_healthy
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "5"
     develop:
       watch:
         - path: ./backend/app
@@ -66,6 +76,11 @@ services:
       AGENT_URL: http://backend:8000/api/v1/agent/agui
     depends_on:
       - backend
+    logging:
+      driver: json-file
+      options:
+        max-size: "10m"
+        max-file: "5"
     develop:
       watch:
         - path: ./frontend/src

frontend/e2e/asistente.spec.ts

@@ -0,0 +1,113 @@
+import { expect, test, type Page } from "@playwright/test";
+
+test.setTimeout(150_000);
+
+async function startFreshAssistant(page: Page) {
+  await page.goto("/login");
+  await page.getByLabel("Username").fill(process.env.ADMIN_USERNAME!);
+  await page.getByLabel("Password").fill(process.env.ADMIN_PASSWORD!);
+  await page.getByRole("button", { name: /sign in/i }).click();
+  await page.waitForURL("/");
+
+  const initialConnect = page.waitForResponse((response) => {
+    if (!response.url().includes("/api/copilotkit") || response.request().method() !== "POST") {
+      return false;
+    }
+    try {
+      return JSON.parse(response.request().postData() ?? "{}").method === "agent/connect";
+    } catch {
+      return false;
+    }
+  });
+  await page.goto("/asistente");
+  await expect(page.getByRole("heading", { name: "Asistente" })).toBeVisible();
+  await (await initialConnect).finished();
+
+  const newConversation = page.getByRole("button", { name: "Nueva conversación" });
+  if (await newConversation.isEnabled()) {
+    await newConversation.click();
+    const reconnect = page.waitForResponse((response) => {
+      if (!response.url().includes("/api/copilotkit") || response.request().method() !== "POST") {
+        return false;
+      }
+      try {
+        return JSON.parse(response.request().postData() ?? "{}").method === "agent/connect";
+      } catch {
+        return false;
+      }
+    });
+    await page.getByRole("button", { name: "Borrar historial" }).click();
+    await (await reconnect).finished();
+    await expect(
+      page.getByRole("textbox", { name: "Escribe tu pregunta…" }),
+    ).toBeEnabled({ timeout: 30_000 });
+  }
+}
+
+async function ask(page: Page, question: string, expectedTool: string) {
+  // The BFF response is the exact CopilotKit stream consumed by the browser.
+  // Checking it catches server-side RUN_ERROR events even if the UI changes.
+  const stream = page.waitForResponse(
+    (response) => {
+      if (
+        !response.url().includes("/api/copilotkit") ||
+        response.request().method() !== "POST"
+      ) {
+        return false;
+      }
+      try {
+        return JSON.parse(response.request().postData() ?? "{}").method === "agent/run";
+      } catch {
+        return false;
+      }
+    },
+  );
+  const composer = page.getByRole("textbox", { name: "Escribe tu pregunta…" });
+  await expect(composer).toBeEnabled({ timeout: 30_000 });
+  await composer.fill(question);
+  const sendButton = page.getByTestId("copilot-send-button");
+  await expect(sendButton).toBeEnabled({ timeout: 30_000 });
+  await sendButton.click();
+  await expect(page.getByText(question, { exact: true }).last()).toBeVisible();
+
+  const response = await stream;
+  await response.finished();
+  const events = await response.text();
+  expect(events).not.toContain("RUN_ERROR");
+  expect(events).toContain(expectedTool);
+
+  // The HTTP stream may finish before CopilotKit has committed the tool run
+  // and released its client-side running state. Waiting for the page action
+  // avoids losing the next Enter keypress during that short interval.
+  await expect(page.getByRole("button", { name: "Nueva conversación" })).toBeEnabled({
+    timeout: 30_000,
+  });
+}
+
+test("Asistente completes Luna's read-only tool flows", async ({ page }) => {
+  const consoleErrors: string[] = [];
+  page.on("console", (message) => {
+    if (message.type() === "error") consoleErrors.push(message.text());
+  });
+
+  await startFreshAssistant(page);
+
+  await ask(page, "What date is it today?", "get_current_date");
+  await ask(page, "List my last 10 transactions.", "get_recent_transactions");
+  await ask(page, "What is my net worth?", "get_net_worth");
+  await ask(page, "How much did I spend today?", "get_daily_spending");
+  await ask(page, "Show my spending by category this month.", "render_spending_summary");
+
+  const spendingCard = page.getByTestId("spending-summary-card");
+  await expect(spendingCard).toBeVisible({ timeout: 30_000 });
+  await expect(page.getByRole("textbox", { name: "Escribe tu pregunta…" })).toBeEnabled({
+    timeout: 30_000,
+  });
+
+  await page.reload();
+  await expect(page.getByRole("heading", { name: "Asistente" })).toBeVisible();
+  await expect(page.getByText("Show my spending by category this month.", { exact: true })).toBeVisible();
+  await expect(page.getByTestId("spending-summary-card")).toBeVisible();
+
+  expect(consoleErrors.join("\n")).not.toContain("ChatClientException");
+});

frontend/e2e/feature-doc.ts

@@ -0,0 +1,127 @@
+import fs from "node:fs";
+import path from "node:path";
+import { test, type Page, type TestInfo } from "@playwright/test";
+import * as narration from "./narration";
+import { renderFinalVideo } from "./video-render";
+import type { Clip } from "./subtitles";
+
+const DEMO = !!process.env.PW_DEMO;
+
+/**
+ * Wraps test.step() so every step of a demo spec produces a captioned
+ * screenshot, and — in PW_DEMO mode — a native Playwright screencast
+ * recording with cursor annotations, chapter-title cards, burned-in
+ * subtitles and (when `say` is available) spoken Spanish narration.
+ * Screenshots/video/subtitles land in e2e-docs/<slug>/ and are also
+ * attached to the Playwright HTML report; save() stitches everything into
+ * a Markdown walkthrough that can be published as-is.
+ */
+export class FeatureDoc {
+  private steps: { title: string; caption: string; file: string }[] = [];
+  private clips: Clip[] = [];
+  private readonly dir: string;
+  private recordingStartedAt = 0;
+
+  constructor(
+    private page: Page,
+    private testInfo: TestInfo,
+    private slug: string,
+    private title: string,
+    private intro: string,
+  ) {
+    this.dir = path.resolve("e2e-docs", slug);
+    fs.rmSync(this.dir, { recursive: true, force: true });
+    fs.mkdirSync(this.dir, { recursive: true });
+  }
+
+  /** Starts the native screencast recording. Call before the first step(). */
+  async start() {
+    if (!DEMO) return;
+    this.recordingStartedAt = Date.now();
+    await this.page.screencast.start({
+      path: path.join(this.dir, "raw.webm"),
+      size: { width: 1920, height: 1080 },
+    });
+    await this.page.screencast.showActions({ cursor: "pointer" });
+  }
+
+  async step(title: string, caption: string, fn: () => Promise<void>) {
+    const narrationPromise = DEMO
+      ? narration.synthesize(caption, this.testInfo.outputDir, this.clips.length)
+      : Promise.resolve(null);
+
+    const stepStart = Date.now();
+    if (DEMO) {
+      await this.page.screencast.showChapter(title, { description: caption, duration: 1500 });
+    }
+
+    await test.step(title, fn);
+
+    const narrationResult = await narrationPromise;
+    if (DEMO) {
+      const elapsed = Date.now() - stepStart;
+      const target = (narrationResult?.durationMs ?? 0) + 300;
+      if (target > elapsed) await this.page.waitForTimeout(target - elapsed);
+    }
+
+    const file = `${String(this.steps.length + 1).padStart(2, "0")}-${title
+      .toLowerCase()
+      .normalize("NFD")
+      .replace(/[̀-ͯ]+/g, "")
+      .replace(/[^a-z0-9]+/g, "-")
+      .replace(/^-|-$/g, "")}.png`;
+    const body = await this.page.screenshot({
+      path: path.join(this.dir, file),
+      animations: "disabled",
+    });
+    await this.testInfo.attach(title, { body, contentType: "image/png" });
+    this.steps.push({ title, caption, file });
+
+    if (DEMO) {
+      this.clips.push({
+        title,
+        caption,
+        file,
+        startMs: stepStart - this.recordingStartedAt,
+        endMs: Date.now() - this.recordingStartedAt,
+        narration: narrationResult,
+      });
+    }
+  }
+
+  async save() {
+    let videoName = "video.mp4";
+    if (DEMO) {
+      await this.page.screencast.stop();
+      const { videoFile, degraded } = await renderFinalVideo({
+        rawWebmPath: path.join(this.dir, "raw.webm"),
+        clips: this.clips,
+        outDir: this.dir,
+      });
+      for (const warning of degraded) console.warn(`[${this.slug}] ${warning}`);
+      videoName = path.basename(videoFile);
+      await this.testInfo.attach("video", {
+        path: videoFile,
+        contentType: videoName.endsWith(".mp4") ? "video/mp4" : "video/webm",
+      });
+    }
+
+    const md = [
+      `# ${this.title}`,
+      "",
+      this.intro,
+      "",
+      `> Generado automáticamente por \`${path.basename(this.testInfo.file)}\` — ${this.steps.length} pasos. El video completo del recorrido está en [${videoName}](${videoName}).`,
+      "",
+      ...this.steps.flatMap((s, i) => [
+        `## ${i + 1}. ${s.title}`,
+        "",
+        s.caption,
+        "",
+        `![${s.title}](${s.file})`,
+        "",
+      ]),
+    ].join("\n");
+    fs.writeFileSync(path.join(this.dir, "index.md"), md);
+  }
+}

frontend/e2e/financiamientos-demo.spec.ts

@@ -0,0 +1,102 @@
+import { test, expect } from "@playwright/test";
+import { FeatureDoc } from "./feature-doc";
+
+/**
+ * Demo walkthrough of the Financiamientos (Tasa Cero) feature. Doubles as an
+ * e2e smoke test and as the generator for e2e-docs/financiamientos/ — a
+ * captioned, screenshot-per-step Markdown doc plus the full video (native
+ * cursor/chapters, burned-in subtitles, spoken narration) in the Playwright
+ * HTML report.
+ */
+// NOTE: do not `test.use({ video: "off" })` here — disabling the fixture
+// video breaks page.screencast's internal sizing (verified: it then records
+// a shrunken frame letterboxed inside the requested canvas). The fixture's
+// own video ends up redundant/unused but harmless.
+
+test("@demo Financiamientos — compras Tasa Cero en cuotas", async ({ page }, testInfo) => {
+  const doc = new FeatureDoc(
+    page,
+    testInfo,
+    "financiamientos",
+    "Financiamientos — Tasa Cero",
+    "WealthySmart trackea las compras BAC Tasa Cero como planes de cuotas mensuales: cada cuota futura ya cuenta en el presupuesto del mes que le toca, en lugar de registrar la compra como un solo pago.",
+  );
+  await doc.start();
+
+  await doc.step(
+    "Iniciar sesión",
+    "El acceso está protegido con usuario y contraseña; la sesión vive en una cookie HTTP-only.",
+    async () => {
+      await page.goto("/login");
+      // CopilotKit mounts its dev web-inspector in dev builds; keep it out of
+      // the recording — it isn't part of the product.
+      await page.addStyleTag({ content: "cpk-web-inspector { display: none !important; }" });
+      await page.getByLabel("Username").fill(process.env.ADMIN_USERNAME!);
+      await page.getByLabel("Password").fill(process.env.ADMIN_PASSWORD!);
+      await expect(page.getByRole("button", { name: /sign in/i })).toBeEnabled();
+    },
+  );
+
+  await doc.step(
+    "Panel de inicio",
+    "Después del login se llega al dashboard Inicio, con el resumen del mes y la navegación lateral por módulos.",
+    async () => {
+      await page.getByRole("button", { name: /sign in/i }).click();
+      await page.waitForURL("/");
+      await expect(page.getByRole("link", { name: "Financiamientos", exact: true })).toBeVisible();
+      await page.waitForLoadState("networkidle");
+    },
+  );
+
+  await doc.step(
+    "Modo privacidad",
+    "El botón de privacidad difumina todos los montos sensibles — útil para compartir pantalla (y para este demo).",
+    async () => {
+      await page.getByRole("button", { name: "Toggle privacy mode" }).click();
+      await expect(page.locator("html")).toHaveClass(/privacy/);
+    },
+  );
+
+  await doc.step(
+    "Página de Financiamientos",
+    "El módulo resume todos los planes Tasa Cero: saldo faltante total, cuánto suman las cuotas de los planes activos cada mes, y cuántos planes siguen vivos.",
+    async () => {
+      await page.getByRole("link", { name: "Financiamientos", exact: true }).click();
+      await page.waitForURL("/financiamientos");
+      await expect(page.getByText("Saldo faltante total")).toBeVisible();
+      await expect(page.getByText("Cuotas por mes (activos)")).toBeVisible();
+      await page.waitForLoadState("networkidle");
+    },
+  );
+
+  await doc.step(
+    "Tabla de planes",
+    "Cada plan muestra el comercio, el avance de cuotas (facturadas vs. totales), el monto de la cuota, el saldo que falta y cuándo cae la próxima cuota.",
+    async () => {
+      const rows = page.getByRole("button", { name: /editar plan de/i });
+      await expect(rows.first()).toBeVisible();
+      expect(await rows.count()).toBeGreaterThan(0);
+      await expect(page.getByRole("columnheader", { name: "Próxima cuota" })).toBeVisible();
+    },
+  );
+
+  await doc.step(
+    "Detalle de un plan",
+    "Al hacer clic en un plan se abre su detalle editable: fecha ancla, número de cuotas y monto. Desde aquí también se puede deshacer la conversión a Tasa Cero.",
+    async () => {
+      await page.getByRole("button", { name: /editar plan de/i }).first().click();
+      await expect(page.getByRole("heading", { name: "Editar plan Tasa Cero" })).toBeVisible();
+    },
+  );
+
+  await doc.step(
+    "Cerrar el detalle",
+    "El plan queda igual que estaba — el recorrido es de solo lectura.",
+    async () => {
+      await page.keyboard.press("Escape");
+      await expect(page.getByRole("heading", { name: "Editar plan Tasa Cero" })).toBeHidden();
+    },
+  );
+
+  await doc.save();
+});

frontend/e2e/narration.ts

@@ -0,0 +1,59 @@
+import { execFile, execFileSync } from "node:child_process";
+import fs from "node:fs";
+import path from "node:path";
+import { promisify } from "node:util";
+
+const execFileAsync = promisify(execFile);
+
+let sayChecked = false;
+let sayAvailable = false;
+
+function hasSay() {
+  if (!sayChecked) {
+    sayChecked = true;
+    try {
+      execFileSync("say", ["-v", "?"], { stdio: "ignore" });
+      sayAvailable = true;
+    } catch {
+      console.warn("`say` not found — skipping TTS narration (subtitles still work).");
+    }
+  }
+  return sayAvailable;
+}
+
+const cache = new Map<string, Promise<{ path: string; durationMs: number } | null>>();
+
+/** Synthesizes Spanish narration for a caption via macOS `say`. Returns null (never throws) if unavailable. */
+export function synthesize(
+  text: string,
+  outDir: string,
+  index: number,
+  voice = "Paulina",
+): Promise<{ path: string; durationMs: number } | null> {
+  const key = `${voice}:${text}`;
+  const cached = cache.get(key);
+  if (cached) return cached;
+
+  const promise = (async () => {
+    if (!hasSay()) return null;
+    fs.mkdirSync(outDir, { recursive: true });
+    const file = path.join(outDir, `narration-${String(index).padStart(2, "0")}.aiff`);
+    try {
+      await execFileAsync("say", ["-v", voice, "-o", file, text]);
+      const { stdout } = await execFileAsync("ffprobe", [
+        "-v", "error",
+        "-show_entries", "format=duration",
+        "-of", "csv=p=0",
+        file,
+      ]);
+      const durationMs = Math.round(parseFloat(stdout.trim()) * 1000);
+      return { path: file, durationMs };
+    } catch (err) {
+      console.warn(`Narration synthesis failed for "${text.slice(0, 40)}…": ${err}`);
+      fs.rmSync(file, { force: true });
+      return null;
+    }
+  })();
+  cache.set(key, promise);
+  return promise;
+}

frontend/e2e/subtitles.ts

@@ -0,0 +1,33 @@
+export interface Clip {
+  title: string;
+  caption: string;
+  file: string;
+  startMs: number;
+  endMs: number;
+  narration: { path: string; durationMs: number } | null;
+}
+
+export function msToSrtTimestamp(ms: number): string {
+  const clamped = Math.max(0, Math.round(ms));
+  const hours = Math.floor(clamped / 3_600_000);
+  const minutes = Math.floor((clamped % 3_600_000) / 60_000);
+  const seconds = Math.floor((clamped % 60_000) / 1000);
+  const millis = clamped % 1000;
+  const pad = (n: number, len = 2) => String(n).padStart(len, "0");
+  return `${pad(hours)}:${pad(minutes)}:${pad(seconds)},${pad(millis, 3)}`;
+}
+
+/** One subtitle cue per step, spanning its full on-screen duration. */
+export function buildSrt(clips: Clip[]): string {
+  return clips
+    .map((clip, i) => {
+      const index = i + 1;
+      return [
+        String(index),
+        `${msToSrtTimestamp(clip.startMs)} --> ${msToSrtTimestamp(clip.endMs)}`,
+        clip.caption,
+        "",
+      ].join("\n");
+    })
+    .join("\n");
+}

frontend/e2e/video-render.ts

@@ -0,0 +1,88 @@
+import { execFile, execFileSync } from "node:child_process";
+import fs from "node:fs";
+import path from "node:path";
+import { promisify } from "node:util";
+import { buildSrt, type Clip } from "./subtitles";
+
+const execFileAsync = promisify(execFile);
+
+function hasFfmpeg() {
+  try {
+    execFileSync("ffmpeg", ["-version"], { stdio: "ignore" });
+    return true;
+  } catch {
+    return false;
+  }
+}
+
+const SUBTITLE_STYLE =
+  "FontSize=22,PrimaryColour=&H00FFFFFF,BackColour=&H80000000,BorderStyle=3,Outline=1,Shadow=0,MarginV=40";
+
+function escapeForFilter(p: string) {
+  // ffmpeg filter arguments treat ':' and '\' specially — escape both.
+  return p.replace(/\\/g, "\\\\").replace(/:/g, "\\:");
+}
+
+export async function renderFinalVideo({
+  rawWebmPath,
+  clips,
+  outDir,
+}: {
+  rawWebmPath: string;
+  clips: Clip[];
+  outDir: string;
+}): Promise<{ videoFile: string; degraded: string[] }> {
+  const degraded: string[] = [];
+  const srtPath = path.join(outDir, "captions.srt");
+  fs.writeFileSync(srtPath, buildSrt(clips));
+
+  if (!hasFfmpeg()) {
+    const dest = path.join(outDir, "video.webm");
+    fs.renameSync(rawWebmPath, dest);
+    degraded.push("ffmpeg not found — kept raw video.webm, no subtitles burned in, no narration.");
+    return { videoFile: dest, degraded };
+  }
+
+  const narrated = clips.filter((c) => c.narration);
+  const mp4Path = path.join(outDir, "video.mp4");
+  const srtArg = `subtitles=${escapeForFilter(srtPath)}:force_style='${SUBTITLE_STYLE}'`;
+
+  if (narrated.length === 0) {
+    degraded.push("No narration available — burned-in subtitles only.");
+    await execFileAsync("ffmpeg", [
+      "-y", "-i", rawWebmPath,
+      "-vf", srtArg,
+      "-c:v", "libx264", "-crf", "20", "-pix_fmt", "yuv420p",
+      "-movflags", "+faststart",
+      "-an",
+      mp4Path,
+    ]);
+  } else {
+    const audioInputs = narrated.flatMap((c) => ["-i", c.narration!.path]);
+    const adelayParts = narrated.map(
+      (c, i) => `[${i + 1}:a]adelay=${Math.max(0, Math.round(c.startMs))}|${Math.max(0, Math.round(c.startMs))}[a${i}]`,
+    );
+    const mixInputs = narrated.map((_, i) => `[a${i}]`).join("");
+    const filterComplex = [
+      `[0:v]${srtArg}[vout]`,
+      ...adelayParts,
+      `${mixInputs}amix=inputs=${narrated.length}:normalize=0[aout]`,
+    ].join(";");
+
+    await execFileAsync("ffmpeg", [
+      "-y", "-i", rawWebmPath, ...audioInputs,
+      "-filter_complex", filterComplex,
+      "-map", "[vout]", "-map", "[aout]",
+      "-c:v", "libx264", "-crf", "20", "-pix_fmt", "yuv420p",
+      "-c:a", "aac",
+      "-shortest",
+      "-movflags", "+faststart",
+      mp4Path,
+    ]);
+  }
+
+  fs.rmSync(rawWebmPath, { force: true });
+  for (const c of narrated) fs.rmSync(c.narration!.path, { force: true });
+
+  return { videoFile: mp4Path, degraded };
+}

frontend/package.json

@@ -9,14 +9,16 @@
     "build": "vite build",
     "preview": "tsx server.ts",
     "typecheck": "tsc --noEmit",
+    "e2e": "playwright test",
+    "demo": "PW_DEMO=1 playwright test --grep @demo",
     "gen:api": "openapi-typescript openapi.json -o src/lib/api-types.gen.ts"
   },
   "dependencies": {
     "@ag-ui/client": "0.0.57",
     "@base-ui/react": "^1.4.1",
-    "@copilotkit/react-core": "1.62.2",
+    "@copilotkit/react-core": "1.62.3",
-    "@copilotkit/react-ui": "1.62.2",
+    "@copilotkit/react-ui": "1.62.3",
-    "@copilotkit/runtime": "1.62.2",
+    "@copilotkit/runtime": "1.62.3",
     "@fontsource-variable/ibm-plex-sans": "^5.2.8",
     "@fontsource-variable/noto-sans": "^5.2.10",
     "@hono/node-server": "^1.14.4",
@@ -41,6 +43,7 @@
     "tw-animate-css": "^1.4.0"
   },
   "devDependencies": {
+    "@playwright/test": "^1.61.1",
     "@tailwindcss/vite": "^4",
     "@types/node": "^20",
     "@types/react": "^19",

frontend/playwright.config.ts

@@ -0,0 +1,52 @@
+import fs from "node:fs";
+import path from "node:path";
+import { fileURLToPath } from "node:url";
+import { defineConfig } from "@playwright/test";
+
+// Demo specs log in with the real dev credentials; pull them from the repo
+// .env so they never live in the test source.
+const repoEnv = path.resolve(path.dirname(fileURLToPath(import.meta.url)), "../.env");
+if (fs.existsSync(repoEnv)) {
+  for (const line of fs.readFileSync(repoEnv, "utf8").split("\n")) {
+    const m = line.match(/^([A-Z_]+)=["']?(.*?)["']?$/);
+    if (m && !(m[1] in process.env)) process.env[m[1]] = m[2];
+  }
+}
+
+export default defineConfig({
+  testDir: "./e2e",
+  outputDir: "./test-results",
+  fullyParallel: false,
+  // Demo runs synthesize narration and run several ffmpeg passes in save();
+  // that can exceed the 30s default, especially with many steps.
+  timeout: process.env.PW_DEMO ? 120_000 : 30_000,
+  reporter: [
+    ["list"],
+    ["html", { outputFolder: "playwright-report", open: "never" }],
+  ],
+  use: {
+    baseURL: "http://localhost:3000",
+    // Demo runs (pnpm demo) pace every action so the recorded video is
+    // watchable by a human; functional e2e runs stay at full speed.
+    launchOptions: {
+      slowMo: process.env.PW_DEMO ? 500 : 0,
+    },
+    locale: "es-CR",
+    timezoneId: "America/Costa_Rica",
+    viewport: { width: 1920, height: 1080 },
+    // Retina-density rendering so doc screenshots stay crisp when zoomed.
+    deviceScaleFactor: 2,
+    // Full recordings are only useful for the paced demo. Keeping them off
+    // for regular e2e avoids making test success depend on artifact uploads.
+    video: process.env.PW_DEMO ? { mode: "on", size: { width: 1920, height: 1080 } } : "off",
+    screenshot: "only-on-failure",
+    trace: process.env.PW_DEMO ? "on" : "on-first-retry",
+  },
+  webServer: {
+    command: "pnpm dev",
+    url: "http://localhost:3000",
+    reuseExistingServer: true,
+    stdout: "ignore",
+    timeout: 60_000,
+  },
+});

frontend/src/components/chat/ChatCards.tsx

@@ -76,7 +76,10 @@ export function SpendingSummaryCard({
   ];
 
   return (
-    <div className="rounded-xl border border-border bg-card text-card-foreground p-4 space-y-4 my-2 shadow-sm">
+    <div
+      data-testid="spending-summary-card"
+      className="rounded-xl border border-border bg-card text-card-foreground p-4 space-y-4 my-2 shadow-sm"
+    >
       {/* Header */}
       <div className="flex items-start justify-between gap-4">
         <div>

frontend/src/lib/api-types.gen.ts

@@ -915,11 +915,9 @@ export interface components {
         AGUIRequest: {
             /**
              * Availableinterrupts
-             * @description List of interrupts that can be resumed by the server
+             * @description Canonical AG-UI interrupts that can be resumed by the server
              */
-            availableInterrupts?: {
+            availableInterrupts?: components["schemas"]["Interrupt"][] | null;
-                [key: string]: unknown;
-            }[] | null;
             /**
              * Context
              * @description List of context objects provided to the agent
@@ -948,11 +946,9 @@ export interface components {
             parent_run_id?: string | null;
             /**
              * Resume
-             * @description Resume payload containing interrupt responses
+             * @description Resume payload for continuing interrupted runs
              */
-            resume?: {
+            resume?: components["schemas"]["ResumeEntry"][] | null;
-                [key: string]: unknown;
-            } | null;
             /**
              * Run Id
              * @description Optional run identifier for tracking
@@ -1373,6 +1369,34 @@ export interface components {
             /** Num Installments */
             num_installments?: number | null;
         };
+        /**
+         * Interrupt
+         * @description A pause carried inside ``RunFinishedEvent.outcome`` when the outcome is
+         *     ``RunFinishedInterruptOutcome``. The client resumes
+         *     by addressing this interrupt in the resume array of the next RunAgentInput.
+         */
+        Interrupt: {
+            /** Expiresat */
+            expiresAt?: string | null;
+            /** Id */
+            id: string;
+            /** Message */
+            message?: string | null;
+            /** Metadata */
+            metadata?: {
+                [key: string]: unknown;
+            } | null;
+            /** Reason */
+            reason: string;
+            /** Responseschema */
+            responseSchema?: {
+                [key: string]: unknown;
+            } | null;
+            /** Toolcallid */
+            toolCallId?: string | null;
+        } & {
+            [key: string]: unknown;
+        };
         /** LoginRequest */
         LoginRequest: {
             /** Password */
@@ -1831,6 +1855,23 @@ export interface components {
                 [key: string]: unknown;
             } | null;
         };
+        /**
+         * ResumeEntry
+         * @description A per-interrupt response in the resume array of a RunAgentInput.
+         */
+        ResumeEntry: {
+            /** Interruptid */
+            interruptId: string;
+            /** Payload */
+            payload?: unknown | null;
+            /**
+             * Status
+             * @enum {string}
+             */
+            status: "resolved" | "cancelled";
+        } & {
+            [key: string]: unknown;
+        };
         /** SalariosSummary */
         SalariosSummary: {
             /** Count */