Add 5 more admin tools + inline write confirmation flow

New tools in admin-tools.ts:
- list_audit_log({limit?}) — recent audit entries (terse: actor, action,
  target, timestamp). Hits /api/v1/admin/audit-log.
- get_platform_stats() — aggregate counts (tenants by status + by plan),
  composed locally from list_tenants until arcadia exposes a real stats
  endpoint.
- list_users({limit?}) — users in the currently-selected tenant via
  /api/v1/users.
- suspend_tenant({slug}) — write tool, suspends a tenant by slug.
- activate_tenant({slug}) — write tool, restores a suspended/deactivated
  tenant.

Inline write confirmation:
- New ConfirmCard component renders below the assistant message that
  proposed a write. Shows tool(args) and Confirm/Deny buttons.
- classifyCalls() splits LLM tool calls into reads/writes. Auto-loop
  runs reads immediately; for any writes, holds them in pendingConfirm
  state instead of dispatching.
- On Confirm: runs writes with allowWrites:true, prepends prior read
  results, continueChat to produce the final answer.
- On Deny: synthesises tool-result messages telling the model the user
  declined; continueChat so it can acknowledge.
- Arcadia-knowledge primer updated to tell the model the user sees an
  inline confirm card automatically — it shouldn't ask in prose first.

Wired into both /ai and /assistant.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
jules
2026-05-01 20:16:41 +10:00
parent fe93f2766c
commit e5cd85fff3
5 changed files with 398 additions and 21 deletions

View File

@@ -32,4 +32,4 @@ Things to keep in mind when assisting:
- Quotas / rate cards / billing config errors usually surface as 402/403 from /api/v1 endpoints — diagnose by checking the tenant's billing-config and api-metering quotas.
- The reference Phoenix app lives at \`reference/arcadia-app/\` in the workspace; its OpenAPI spec is at /api/openapi (sync via \`node ../lib-arcadia-client/scripts/sync-spec.mjs\`).
When the user asks something that maps to a tool, call it. When they ask about a concept, explain it from this primer in plain language. When they ask to do something destructive, summarise the impact in one sentence and ask for confirmation before suggesting a tool call.`
When the user asks something that maps to a tool, call it. When they ask about a concept, explain it from this primer in plain language. Write tools (suspend_tenant, activate_tenant) prompt the operator with an inline confirm card before they actually run — you do not need to ask in prose first; just call the tool and the user will see the confirmation UI. If the user denies a write, do not retry it; ask what they'd like to do differently.`