Files
accounted/lib/agent-context/agent-competence.ts
T
Jakob Wennberg 4b51af3d80 feat(agent): 'Vad din agent vet' page rendering the ledger context (P2) (#935)
* feat(agent): 'Vad din agent vet' page rendering the ledger context (P2)

The human-facing surface for the openwiki ledger-context: a read-only page
that renders the exact payload the AI agent reads (Accounted://ledger/context
+ the briefing digest) as a legible profile of how this company books.

- Route app/(dashboard)/agent-knowledge (server component) calls the shared
  buildLedgerContext(supabase, companyId) directly: one payload, two
  renderers, no new API or data path.
- Sections mirror the payload 1:1: coverage/freshness strip, counterparty
  patterns (monochrome confidence bars + seen/agree evidence), supplier
  patterns, explicit rules shown as authoritative instructions distinct from
  observed patterns, account usage, VAT profile, conventions.
- Nav entry in the Analys group (icon Brain), ungated so it doubles as an
  upsell; flip requiredCapability to paywall.
- Design per .claude/rules/design.md (PageHeader, Card, Table, Badge,
  AccountNumber BAS tooltips); sv + en strings (agentKnowledge namespace).
  VAT/BAS labels stay Swedish in both locales per i18n rules.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(agent): deep entity-resolved analysis + radial graph for the knowledge page

Reworks the 'Vad din agent vet' page from tables into a radial-hub graph
driven by a new full-history deep analysis, per founder feedback.

- fix(rpc): median_booking_lag_days now measures real posting promptness via
  committed_at, not entry_date (which the bank flow sets to the transaction
  date, giving a ~0 tautology: 151/152 on prod). migration 20260708120000.
- feat(rpc): get_ledger_deep_context (migration 20260708130000): full-history,
  deterministic, read-side. Merges counterparties by normalize_counterparty_key
  (e.g. Claude = 14 bookings across 12 name variants, weekly, 9 710 kr, always
  5420), mines booked verifikat for SEK spend (coalesce amount_sek), detects
  recurrence cadence, dominant account + share, plus supplier entities. Storno
  excluded, corrections kept; 19xx/26xx excluded from the dominant contra.
- LedgerGraph: radial SVG (company center, accounts inner ring, payees outer
  ring), hover/focus reveals variants + spend + cadence + account. Keyboard
  focusable nodes with per-node accessible names + a screen-reader data table.
- Page fetches the deep context alongside the light context; coverage strip
  gains tracked-payee / recurring / tracked-spend stats. sv + en strings.
- 14 pg tests (light + deep) green; both RPCs applied to prod + version-matched.

Reviewed by an adversarial multi-lens pass (accounting/SQL, frontend/a11y,
prod-fact verification); all four verified findings fixed (SEK currency,
storno-lag guard, keyboard a11y, spacing tokens).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(agent): gentle mount fade-in for the radial map (reduced-motion safe)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(agent): render the page for a rules-only company (empty-state edge case)

isEmpty ignored explicit_rules, so a company with configured mapping rules
but no posted transactions hit the 'hasn't learned anything' empty state and
lost its rules section. Rules are independent of bookings. (CodeRabbit)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(agent): show Kompetens (skills) + Fakta (memory) on the knowledge page

The 'Vad din agent vet' page now shows the full picture of what the agent
knows: alongside the booking map, a compact read-only view of its Kompetens
(the Swedish accounting/tax knowledge atoms it ships with, grouped by
tier as chips with active/dormant state) and the Fakta it remembers (top
learned facts with kind + source), each linking to /settings/assistant for
full management. Server-rendered via a new buildAgentCompetence() that
mirrors GET /api/agent/skills + /api/agent/memory. Also renders in the
no-bookings case so a new company still sees its agent's competence.
sv + en strings.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* refactor(agent): restructure knowledge page - hero graph + tabbed detail

Declutters the page per feedback: the booking map is the always-visible hero,
and the supporting detail (Kompetens · Minne · Regler & profil) moves into
tabs so only one view shows at a time instead of a long card stack. Split
AgentCompetenceSections into standalone CompetenceCard + FactsCard for the
tabs; removed the top stat row on request. sv + en.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(agent): Reconciliation Aurora rewrite of the ledger knowledge graph

Full rewrite of LedgerGraph: node area = sqrt(spend), colour = cadence,
shape = supplier/counterparty, confidence = depth-of-field; on-mount
descriptor-collapse animation with xN badge; cadence pulse veins;
deterministic seeded layout; framer-motion only (no new deps); keyboard
navigation, reduced-motion and sr-only support. Build-verified; 3-lens
adversarial review findings fixed.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(agent): sample-size-honest confidence in the ledger knowledge graph

dominant_account_share was raw cnt/total, so a counterparty with a single
booking rendered as '100% säkerhet': fake certainty by construction (the
data_quality_master Item-C / P3 finding). New migration replaces
get_ledger_deep_context with a Laplace-smoothed share (cnt+1)/(total+2)
(1/1 -> 0.67, 3/3 -> 0.80) and exposes the raw evidence as
dominant_account_count / dominant_account_total. The detail card now shows
'Bokförd hit i k av n fall' under the confidence bar; the existing focus
buckets, stroke widths and percent labels inherit the honest value
unchanged. pg-real test updated to guard the n=1 case.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-07-12 21:25:34 +02:00

100 lines
3.4 KiB
TypeScript

import type { SupabaseClient } from '@supabase/supabase-js'
// Server-side read of the agent's competence (the domain-knowledge "atoms" it
// ships with) and its top learned facts (memory), for the read-only overview
// on the "Vad din agent vet" page. Mirrors GET /api/agent/skills and
// GET /api/agent/memory so the two surfaces stay consistent; the full editable
// management lives in /settings/assistant.
export type AtomTier = 'horizontal' | 'vertical' | 'modifier'
export interface AgentAtom {
id: string
tier: AtomTier
title: string
description: string
/** horizontal atoms apply to every company; vertical/modifier only when the
* composer selected them into this company's profile. */
active: boolean
}
export type FactKind = 'fact' | 'preference' | 'pattern' | 'correction'
export type FactSource = 'composer' | 'user_taught' | 'agent_learned' | 'derived'
export interface AgentFact {
id: string
kind: FactKind
content: string
source: FactSource
is_pinned: boolean
}
export interface AgentCompetence {
atoms: AgentAtom[]
facts: AgentFact[]
/** Total active facts (before the overview cap), so the count is honest. */
factsActiveTotal: number
}
const FACTS_LIMIT = 12
export async function buildAgentCompetence(
supabase: SupabaseClient,
companyId: string,
): Promise<AgentCompetence> {
const [atomsRes, profileRes, factsRes, factsCountRes] = await Promise.all([
// The atom registry is global product content, not tenant data.
supabase
.from('agent_atom_registry')
.select('id, tier, title, description')
.eq('is_active', true)
.eq('mcp_exposed', true)
.is('parent_atom_id', null)
.order('tier', { ascending: true })
.order('title', { ascending: true }),
supabase
.from('agent_profiles')
.select('vertical_atoms, modifier_atoms')
.eq('company_id', companyId)
.maybeSingle(),
supabase
.from('agent_memory')
.select('id, kind, content, source, is_pinned')
.eq('company_id', companyId)
.eq('is_active', true)
.order('is_pinned', { ascending: false })
.order('relevance_score', { ascending: false })
.order('last_accessed_at', { ascending: false, nullsFirst: false })
.order('created_at', { ascending: false })
.limit(FACTS_LIMIT),
supabase
.from('agent_memory')
.select('id', { count: 'exact', head: true })
.eq('company_id', companyId)
.eq('is_active', true),
])
if (atomsRes.error) throw new Error(`agent skills failed: ${atomsRes.error.message}`)
if (factsRes.error) throw new Error(`agent memory failed: ${factsRes.error.message}`)
const verticalActive = new Set((profileRes.data?.vertical_atoms as string[] | null) ?? [])
const modifierActive = new Set((profileRes.data?.modifier_atoms as string[] | null) ?? [])
const atoms: AgentAtom[] = (atomsRes.data ?? []).map((a) => {
const tier = a.tier as AtomTier
const active =
tier === 'horizontal' ? true : tier === 'vertical' ? verticalActive.has(a.id) : modifierActive.has(a.id)
return { id: a.id, tier, title: a.title, description: a.description, active }
})
const facts: AgentFact[] = (factsRes.data ?? []).map((f) => ({
id: f.id,
kind: f.kind as FactKind,
content: f.content,
source: f.source as FactSource,
is_pinned: f.is_pinned,
}))
return { atoms, facts, factsActiveTotal: factsCountRes.count ?? facts.length }
}