@capagents/forgeqe 2.3.12 → 2.3.14

package/HOW_TO_USE.md

@@ -623,6 +623,12 @@ The slash commands control the session and show a few things directly (`/help` l
 | `/runs`, `/reports` | The runs and reports in the reports folder, newest first |
 | `/jobs` | The scheduled jobs: when each runs next, and how its last run ended |
 | `/knowledge` | The product knowledge the agents read (`.forgeqe/knowledge`) |
+| `/memory` | Page memory: the sites and pages ForgeQE remembers, and their flows |
+| `/guardrails` | The rules every agent follows here |
+| `/doctor` | Check what ForgeQE needs: programs, sign-ins, and the services it reaches |
+| `/settings` | `forgeqe.yaml`: where it is and what it sets, opened to edit |
+| `/home` | Back to the start screen; the session stays |
+| `/docs` | The user guide |
 | `/generated` | How much of this repository's code ForgeQE wrote, and how much is still there |
 | `/init` | Set ForgeQE up in this folder: `forgeqe.yaml`, `llms.json`, editable prompts, skills, knowledge |
 | `/skills [name]` | The skills each agent can use, or one skill's instructions |
@@ -756,9 +762,11 @@ Over the conversation: **Files** (each file read ◉, written ✚, or edited ✎
 
 **Links.** Report folders, report files, and web addresses in the chat are links: Cmd-click (Ctrl-click on Windows and Linux) opens them in terminals that support links, such as VS Code, iTerm2, Windows Terminal, and recent GNOME Terminal. A path that no longer exists stays plain text.
 
-**Setup checklist.** Until everything is set up, the start screen shows how many of the five things most features rest on are set up: **Model** (a live model profile), **Coding agent**, **Work items** (Azure DevOps, Jira, TestRail, Zephyr, qTest, or Xray), **Domain**, and **Notifications**. In a terminal 110 columns or wider it is the sidebar's **Get set up**: each finished item with what it found, and the next one as a card whose **▸ Set up** puts its steps in the chat (for **Work items**, it runs `/auth`). Narrower, it is one **Setup** line under the composer, and **▸ how to set up** gives the steps for every missing one. The checks are the same ones `/features` uses, so the two always agree.
+**Setup checklist.** Until everything is set up, the start screen shows how many of the five things most features rest on are set up: **Model** (a live model profile), **Coding agent**, **Work items** (Azure DevOps, Jira, TestRail, Zephyr, qTest, or Xray), **Domain**, and **Notifications**. In a terminal 110 columns or wider it is the sidebar's **Get set up**: each finished item with what it found, and the next one as a card with **▸ Set up** (its steps in the chat; for **Work items**, it runs `/auth`) and **skip**. A skipped item is kept in `.forgeqe/setup.json` and not asked about again. Narrower, it is one **Setup** line with **▸ how to set up** and **skip**. The checks are the same ones `/features` uses, so the two always agree.
 
-**Sidebar.** Under setup, **Work** opens **Runs**, **Reports**, **Jobs** and **Knowledge** (`/runs`, `/reports`, `/jobs`, `/knowledge`) with how many of each there are, and **Defects** (with a tracker set up) puts a request for the open defects in the composer. **System** opens **Features**, **Skills**, **Environments**, **Models**, **Sign in** and **Logs**. The status line shows the branch, the model (click it to change), the tracker, and when the next scheduled job runs.
+**Sidebar and rail.** The sidebar has three groups. **Work**: **Home**, **This session** (once you have asked something), **Runs**, **Reports**, **Jobs**, and **Defects** (with a tracker set up). **Knowledge**: **Page memory**, **Test cases** (with a tracker), **Guardrails**, **Product** (the knowledge files) and **Skills**. **System**: **Models**, **Sign in**, **Environments**, **Doctor**, **Settings**, **Help** and **Docs**. Each shows how many there are and opens its list (`/runs`, `/reports`, `/jobs`, `/memory`, `/guardrails`, `/knowledge`, `/skills`, `/doctor`, `/settings`, `/help`, `/docs`); **Defects** and **Test cases** put a request in the composer, since the agent reads them from the tracker. Narrower than 110 columns, and beside the chat at every width, the sidebar folds to a rail of its icons, so the start screen is always one click away: **Home** (or `/home`) shows it with the session still open, and **▸ Back to the session** or any request returns to it.
+
+**Needs you and Today.** Once there are runs, the start screen shows what needs you (runs that failed this week and have not passed since, and jobs whose last run failed, each with **open** and **rerun**) and what ran today. The greeting says how many runs there were today and how many failed. The model is in the composer beside **⏎ Send**: click it to change it. The status line shows the branch, the tracker, and when the next scheduled job runs.
 
 **Command palette.** Ctrl-P opens a palette of every action, command, profile, and example request; type a few letters to find one ("rr" finds *Refine my request*, "auth" finds the sign-in commands), ↑/↓ to choose, Enter to run it. Example requests are put in the prompt for you to edit, never sent straight away.