The CR-hardcoded today broke two scenarios: the owner traveling, and
any future non-CR user. Now the provider sends the browser's IANA
timezone (X-Client-Timezone) with every CopilotKit request — the
runtime forwards x-* headers to the agent on its own — and the backend
binds it to a per-request ContextVar next to the DB session.
get_current_date and the future-cuota bounds use it; the tool also
reports the timezone so the model can echo it. Unknown or absent zones
(n8n posts, tests) fall back to Costa Rica; comma-joined duplicate
header values are tolerated.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Prod showed the failure mode after the date fix: get_current_date
returned the right day, but the model answered "¿cuánto he gastado
hoy?" from cycle-level aggregates (the only spend tools it had) and
concluded ₡0. Give it a day-grained tool — per-day CRC totals mirroring
/analytics/daily-spending (COMPRA only, no installment anchors, no
future cuotas) — and a prompt rule to match tool to time grain.
Verified: fresh thread now calls get_current_date →
get_daily_spending(2026-07-04, 2026-07-05) and answers correctly.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Two bugs from prod (server clock is UTC, user is UTC-6):
- get_recent_transactions returned future-dated Tasa Cero cuotas; it now
excludes anything dated after the user's today, same rule as
/transactions/recent.
- "¿Cuánto he gastado hoy?" answered for the wrong day: the prompt baked
date.today() in at boot — frozen from startup AND in server-UTC (8 pm
in Costa Rica is already tomorrow in UTC). The prompt no longer carries
a date; a new get_current_date tool returns today in CR time plus the
active billing cycle, and the prompt directs the model to call it for
any relative date reference. today_cr() lives in timeutil (CR has no
DST, fixed UTC-6).
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
After the client returns a render tool's result, the model sometimes
re-issues the identical call with a fresh id on the follow-up run,
painting a second copy of the spending-summary card (observed live on
MAF 1.10 / CK 1.62). DeduplicateToolCallMiddleware now tracks which
render tools already ran in the current user turn and drops repeats —
their streamed TOOL_CALL_* events and their entries in the run's
MESSAGES_SNAPSHOT. The system prompt also tells the model the card is
already displayed once its "ok" result is present.
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
CK 1.60+ validates generated a2ui ops against a component catalog before
painting, and our agent's ops fail validation — surfaces hang at
"Building interface" forever (MAF also drops RunAgentInput.context, so
the catalog/guidelines never even reach the model). Disable a2ui end to
end until the pipeline matures:
- server.ts: a2ui { enabled: false }; RENDER_TOOLS no longer includes
render_a2ui
- App.tsx: remove the a2ui provider prop
- agent.py: prompt now asks for clean markdown tables for lists and
structured data; render_spending_summary card guidance unchanged
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Wires up an OpenAI-backed MAF agent that exposes WealthySmart
data through tool calls (recent transactions, cycle summary,
analytics, pensions). Pulls in agent-framework + AG-UI adapter
+ OpenAI client deps.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
