@flowapt/flowiq-cli 0.6.2 → 0.6.3

package/README.md

@@ -917,8 +917,11 @@ are full-replace within the row.
 
 The client-hours ledger. Every org's package includes **10 hours of Flowapt
 work per calendar month**; every piece of client work gets logged against it —
-manually here, or automatically by Claude sessions via the FlowIQ MCP's
-`log_client_hours` tool. Clients see their own usage on the Client Console;
+manually here, or automatically by Claude sessions. **The CLI is the only
+way to log hours:** the FlowIQ MCP's `log_client_hours` tool was removed on
+29 Aug 2026, because the MCP advertises every tool to every connection and a
+staff-only write does not belong on a client-facing surface. The MCP keeps
+`get_client_hours` (read). Clients see their own usage on the Client Console;
 the cross-org view lives in the super-admin Changelog dialog → Client hours.
 
 ```bash
@@ -1126,9 +1129,10 @@ Full new-client bootstrap from the terminal:
 ```bash
 flowiq org create --name "New Client"
 flowiq agent create <new_org_id> --name "Zara" --make-active
-flowiq agent config <new_org_id> --model gpt-5.4-mini --use-settings-prompt
 flowiq prompts pull <new_org_id>   # edit → push
 ```
+(No `agent config` step any more — since 29 Aug 2026 a new agent is born on the
+house default: `gpt-5.6-luna`, `reasoning_effort high`, `use_settings_prompt` ON.)
 
 ### Agents — `flowiq agent list|create <org>`
 
@@ -1142,9 +1146,16 @@ flowiq agent create <organization_id> --name "Zara" \
 
 `create` inserts a new agent (`created_by` = your staff-key identity), optionally
 seeds its prompt into a single "Main" section, and — with `--make-active` — sets
-it as the org's `active_whatsapp_agent`. New agents start on the app default
-model; set the house model afterwards with `agent config … --model gpt-5.4-mini
---use-settings-prompt`.
+it as the org's `active_whatsapp_agent`.
+
+**Since 29 Aug 2026 a new agent is born configured** — `gpt-5.6-luna`,
+`reasoning_effort high`, `use_settings_prompt` ON — the same house default the
+web UI's create button writes. You no longer have to follow `create` with an
+`agent config --model … --use-settings-prompt`; that step used to be the "silent
+killer" (a perfect prompt ignored because the toggle was still off) and was
+missed on 14 of 93 agents. Turning the flag on is safe on a blank agent: the
+runtime needs BOTH the flag and a non-empty prompt, so it only starts mattering
+once you push a real one. `agent config` still overrides any of it per agent.
 
 ### Targeting a specific agent — `--agent <id>`
 
@@ -1155,7 +1166,7 @@ on the org's **active** agent. To target a **different** agent, pass `--agent <i
 ```bash
 flowiq prompts pull <org> --agent <agent_id>      # pull a NON-active agent's prompt
 flowiq prompts push <slug>                          # pushes back to that same agent (id is in the file)
-flowiq agent config <org> --agent <agent_id> --model gpt-5.4-mini
+flowiq agent config <org> --agent <agent_id> --model gpt-5.6-luna
 ```
 
 `pull` records the agent id in the JSON, so `push` always writes back to the exact
@@ -1173,7 +1184,7 @@ Set an allowlisted set of the active agent's config fields (the prompt-builder
 
 ```bash
 flowiq agent config <organization_id>                        # show current
-flowiq agent config <organization_id> --use-settings-prompt --model gpt-5.4-mini \
+flowiq agent config <organization_id> --use-settings-prompt --model gpt-5.6-luna \
   --rename Zara --tool woo_order_build=true --tool view_cart_tool=true --discount true
 flowiq agent config <organization_id> --test-contact-number 27000000001 --test-contact-name "QA Bot"
 flowiq agent config <organization_id> --model gpt-5.6-luna --reasoning-effort high

package/TEAM-GUIDE.md

@@ -95,7 +95,7 @@ When you see it, run `npm i -g @flowapt/flowiq-cli` — a stale version also mea
 | Ask a client's WooCommerce store anything (read-only) | `flowiq woo get <org_id> orders --q status=completed --all` |
 | Pull every matching record, not just the first page | add `--all` (bounded — it prints `⚠ TRUNCATED` if it stops early, so a partial answer never looks complete) |
 | Feed store data into jq / a file | stdout is the payload only, banner goes to stderr: `flowiq shopify get <org> orders.json \| jq -r '.orders[].name'` · or `--out ./orders.json` |
-| See an org's agents / create one | `flowiq agent list <org_id>` / `flowiq agent create <org_id> --name "…"` |
+| See an org's agents / create one | `flowiq agent list <org_id>` / `flowiq agent create <org_id> --name "…"` — a new agent arrives ready to work (gpt-5.6-luna, high reasoning, prompt switched ON); no follow-up `agent config` needed |
 | Change agent model / tool flags | `flowiq agent config <org_id> --model … --tool view_cart_tool=true` |
 | Set the house model + reasoning tier | `flowiq agent config <org_id> --model gpt-5.6-luna --reasoning-effort high` |
 | Agent says an in-stock product "isn't showing" | `flowiq agent config <org_id> --tool collapse_product_variants=true` — the search cap counts VARIANT rows until this is on |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@flowapt/flowiq-cli",
-  "version": "0.6.2",
+  "version": "0.6.3",
   "description": "Command-line tool for FlowIQ staff: round-trip agent prompts, questionnaires, fine-tuning, pin-board tasks, webhooks, templates, agent-updates, chat exports, and live agent testing without ever touching service-role credentials.",
   "type": "module",
   "bin": {