mirror of
https://github.com/jparkerweb/plan2code.git
synced 2026-11-16 04:45:33 -08:00
Document the setup page and Agents & models split, and fold the v4.0.0 notes into v3.0.0
AI Assisted
This commit is contained in:
1 parent
61f27f81ab
commit
c02894ac2a
10 files changed
+195
-47
No files matched your search
@@ -12,10 +12,17 @@ Each session stays short, and the specs on disk carry everything from one sessio
|
||||
- **Node.js 18 or newer.** Check with `node --version`. No Node? Get it from [nodejs.org](https://nodejs.org/) (the LTS download), or run `winget install OpenJS.NodeJS.LTS` on Windows, `brew install node` on macOS, or use `nvm` on Linux. Then open a new terminal.
|
||||
- **Start from your project.** Open your terminal in the project you want to work on (`cd` into it) before you run anything. Plan2Code works on the folder you start it in.
|
||||
- **Ways in.** `plan2code` (Claude Code, Devin or Codex), or type `/plan2code` in your agent (`$plan2code` in Codex).
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first.
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first, or let the `plan2code` command's setup page walk you through it.
|
||||
|
||||
Not installed yet? The install steps are in the [README](../README.md#install-and-start).
|
||||
|
||||
> **Running `plan2code` with no agent installed** opens a setup page instead of a dashboard: it
|
||||
> lists each built-in as found, found outside PATH or not found, with its install commands for
|
||||
> your system and an Install page link. Install one, press **Check again**, then **Start with
|
||||
> this agent** and the run carries on in the same tab. On a machine with no browser (over SSH, a
|
||||
> server) it prints the install steps instead and exits with code 127. The rest of this
|
||||
> walkthrough assumes an agent is already in place.
|
||||
|
||||
---
|
||||
|
||||
## Session 1: Plan
|
||||
|
||||
+141
-16
@@ -294,6 +294,34 @@ on your own machine. An agent working in a cloud VM, a container or over SSH
|
||||
stays in the terminal: a `127.0.0.1` link from somewhere else is a link you
|
||||
cannot open.
|
||||
|
||||
### When no agent is found
|
||||
|
||||
The console does not always have an agent behind it. When `plan2code` finds no agent it can start
|
||||
(no built-in and no working custom agent), it opens the console anyway on its **setup**
|
||||
page: the one session with no agent attached, whose only job is getting you one. The desktop app
|
||||
opens the same page in its window from a **Set up an agent** button.
|
||||
|
||||
Each built-in is listed with what Plan2Code found when it looked (the same lookup the `plan2code`
|
||||
command and the app use, so all three agree):
|
||||
|
||||
- **Found**: installed and ready. **Start with this agent** picks it.
|
||||
- **Found outside PATH**: installed, but not where `PATH` looks (it turned up on the saved
|
||||
Windows PATH, in npm's global folder or in its documented install folder). **Use it from here**
|
||||
saves that location, no `PATH` editing needed; the steps for doing it by hand are there too.
|
||||
- **Not found**: not installed, or not anywhere Plan2Code looks. Its install commands for your
|
||||
system are listed, each with a Copy button, beside an **Install page** link.
|
||||
|
||||
**Check again** re-runs the lookup without restarting anything, so an agent you just installed
|
||||
turns up. Under the list are four starter templates (GitHub Copilot CLI, OpenCode, Gemini CLI,
|
||||
Pi): starting setups for agent CLIs Plan2Code does not ship, which fill in the same form as adding
|
||||
an agent by hand and save as custom agents. The page's Help has a *Setting up an agent* topic, and
|
||||
signing in to the agent itself is always your own step.
|
||||
|
||||
Pressing Start shows a "Starting <agent>..." pane while the new agent's session opens, then the
|
||||
tab moves to it by itself. If the move never comes, a line after about two minutes points you at
|
||||
the terminal and offers a way back to the list. Inside the app there is no Start: the app hears
|
||||
that the page found an agent, closes the page and picks it on the launch card.
|
||||
|
||||
### Your role
|
||||
|
||||
The last control on *User Preferences*' Appearance tab (the gear button) is **Role**:
|
||||
@@ -946,7 +974,8 @@ Ghoul Rush at 65).
|
||||
bag is empty. Each room's door opens
|
||||
once you grab its key, often up on a shelf. A run starts in **the Long
|
||||
Hall**, an easy walk with only zombies, then goes **stage** by stage:
|
||||
three rooms, then a boss, and beating it opens the door. Out of the hall
|
||||
three rooms, a bonus ride, then a boss (a big **BOSS FIGHT** card shows the
|
||||
boss, its name and a menacing line first, and the fight waits for a key press), and beating it opens the door. Out of the hall
|
||||
and out of each boss's room you **choose the next stage** from two
|
||||
(one, once a single stage is left) never played that run, each card
|
||||
showing the stage with its boss standing in it: left and right pick one
|
||||
@@ -970,7 +999,13 @@ Ghoul Rush at 65).
|
||||
the last steps the chain, which multiplies kills up to x10. The rooms bring
|
||||
pits, one-way shelves, crumbling boards and falling chandeliers that crush
|
||||
whatever is below (a monster crushed counts double). Five stages so
|
||||
far: **the Manor**, the **Foyer**, the **Portrait Gallery**, the **Library**, the **Ballroom**
|
||||
far: **the Manor**, the **Foyer**, the **Portrait Gallery**, the **Library**, the **Grand Banister**
|
||||
(a **bonus round**: you slide down the grand staircase's banister for about a minute,
|
||||
jumping vases, candlesticks and the breaks in the rail, ducking hanging portrait
|
||||
frames and chandeliers on a pendulum (brake or lean to time them), shooting ghostly
|
||||
butlers and cobwebs, and jumping with DOWN held to dive onto the brass under-rail
|
||||
where the track splits; five hearts of your own, as in the other bonus rounds),
|
||||
the **Ballroom**
|
||||
(the **Rotting Gourd**, a giant rotten pumpkin that picks one of three
|
||||
moves at random, never one three times running: a hop to where you stood,
|
||||
its shadow showing where, that shakes loose gourdlings; a spit of two
|
||||
@@ -990,7 +1025,14 @@ Ghoul Rush at 65).
|
||||
around you on shadows, and he raises up to two skeletons out of the floor),
|
||||
and **the Graveyard**, out
|
||||
under the night sky: the **Lychgate**, **Open Graves**, **Mausoleum Row**
|
||||
and **Angel's Rest**. Its monsters are its own: **grasping hands** that lie
|
||||
and **Angel's Rest**; between the Row and Angel's Rest is a **bonus round**,
|
||||
**the Midnight Hearse**: you hijack a runaway hearse and tear down the
|
||||
cemetery road for about a minute, switching between the road and the grass
|
||||
verge at the lane gates to get round fallen oaks and hedge walls, jumping
|
||||
open graves and headstones, ducking branches and the lychgate arch and
|
||||
shooting grasping hands and crows, with the lamp kept lit by lanterns on the
|
||||
road (a hit throws a coffin out ahead, and the ghoul that sits up in it is
|
||||
worth shooting). Its monsters are its own: **grasping hands** that lie
|
||||
unseen under the dirt, burst up as you pass and creep along under the
|
||||
ground after you; **mourners** whose wail slows you to half speed for a
|
||||
moment if you are close; **grave robbers** who dig in and come up behind
|
||||
@@ -1049,12 +1091,32 @@ Ghoul Rush at 65).
|
||||
Choirmaster**, at his organ. Silence the four pipes to open him: each pipe
|
||||
takes a handful of bolts, a sounding pipe spews a ghost now and then, and
|
||||
while any pipe sounds he cannot be hurt. Once all four are silent, shoot
|
||||
him. Between those he raises his baton and a column of notes flies at you
|
||||
along the lines of a staff with one gap in it: mind the gap in each column
|
||||
and be at its height (the floor or one of the boards) as it passes. At
|
||||
half his health the hymn quickens: the notes fly faster, now and then a
|
||||
second column follows close behind, and the pipes come back one by one,
|
||||
each sounding again in turn.
|
||||
him, but not for long: after four more columns of notes, fresh pipes drop
|
||||
in from the roof and you must silence them again. Between those he raises
|
||||
his baton and a column of notes flies at you along the lines of a staff
|
||||
with one gap in it: mind the gap in each column and be at its height (the
|
||||
floor or one of the boards) as it passes. Each column has its own speed,
|
||||
some far faster than others (a hot edge and a long tail) and some slower (a
|
||||
cold edge and a short tail). At half his health the hymn quickens: the
|
||||
notes fly faster and now and then a second column follows close behind.
|
||||
Between the Organ Loft and the Choir is a
|
||||
**bonus round**, **Holy Roller**: an endless-runner seen from behind. You
|
||||
surf a runaway church pew down the nave's aisle toward the altar, in three
|
||||
lanes, faster and faster for about a minute, with stone pillars, stained
|
||||
glass and pews rushing past in candlelight. LEFT and RIGHT change lane (a
|
||||
press at the edge bumps the wall), UP jumps, DOWN slides (in the air it
|
||||
fast-falls), and holding space shoots straight down your lane. Switch lane
|
||||
around the pillars, confessionals and crosswise pews; jump the kneelers,
|
||||
candle stands, flagstone cracks and open crypt hatches; slide under the
|
||||
swinging censers, hanging banners and fallen beams; shoot the gargoyles
|
||||
that drop from the arches (two bolts) or shoot a bell rope to ring its bell
|
||||
and stun the gargoyles ahead. Rows of golden wax souls run along the lanes
|
||||
(arcs over jumps, lines through slides) and build a combo, and a halo
|
||||
pulls the souls beside you in for a few seconds. Taking most of the souls
|
||||
is worth a Lucky Die. It plays for five hearts of its own, so a hit costs a
|
||||
heart, never a life, and shoves you into a safe lane; lose all five and the
|
||||
round ends with nothing and the run goes on to the Choir; reach the end and
|
||||
you earn three to nine Lucky Dice.
|
||||
A sixth stage, **Blackmoor Sanatorium**, is a derelict asylum of cracked
|
||||
green tile: **Admissions**, the **Hydrotherapy Baths**, the **Surgical
|
||||
Theater** and **the Night Ward**. Its monsters: **orderlies**, huge and
|
||||
@@ -1096,7 +1158,19 @@ Ghoul Rush at 65).
|
||||
moment, the time to shoot it for double damage, then pounces where you
|
||||
stand (watch the shadow on the grass); up close it swipes, and its howl
|
||||
calls moonhounds. At half its health the moon comes full: it waits less,
|
||||
pounces twice in a row, and its howl calls grown hounds.
|
||||
pounces twice in a row, and its howl calls grown hounds. Between the
|
||||
Square and the Green is a **bonus round**, **Torch Mob**: you steal a hay
|
||||
wagon and race out of Hollow End down the cobbled road and over the old
|
||||
stone bridge, about a minute and ten seconds, with the village chasing you.
|
||||
Jump the barrels, crates, ditches and spooked horses, duck the washing
|
||||
lines and inn signs (down also brakes the wagon), and shoot or dodge the
|
||||
pitchforks and torches the villagers hurl from windows and roofs (a torch
|
||||
that lands sets the hay alight). The **mob** behind you closes in when you
|
||||
brake, get hit or burn, and falls back on clean stretches and when you
|
||||
shoot their torches; if it catches the wagon it costs a heart, and the
|
||||
collapsed bridge must be jumped off its ramp. Keeping the mob far behind
|
||||
is worth a Lucky Die. It plays for five hearts of its own and pays three
|
||||
to nine Lucky Dice.
|
||||
An eighth stage, **the Deep Seam Mine**, goes underground, where every room
|
||||
is always dark: **the Mine Shaft** (ride the cage lifts up and down),
|
||||
**the Flooded Tunnels** (knee-deep water slows you and your steps splash),
|
||||
@@ -1224,9 +1298,40 @@ Ghoul Rush at 65).
|
||||
all five and the round ends with nothing and the run goes on to the Widow;
|
||||
reach the snowbank and you earn three to nine Lucky Dice (hearts left,
|
||||
obstacles passed untouched, things shot and souls and Cocoa taken).
|
||||
**Gallows Bog** is a stage of three walked rooms (the Sunken Boardwalk,
|
||||
Cypress Hollow and the Stilt House), a fan-boat ride and the Drowning Pool.
|
||||
Its own rule is **mud**: on a span of it Planny sinks the longer he stands,
|
||||
the run sags to a crawl and a jump to a low hop over about two and a half
|
||||
seconds. Dry floor, the air, a board over the mud or **Stilt Boots** (ten
|
||||
seconds, found only here) let go of it, and the sink drains away. Its monsters: the **lurker**,
|
||||
two eyes at the waterline that nothing touches or shoots until you come
|
||||
within nine units, then it snaps out at you and sinks back; the **leech
|
||||
swarm**, which drifts at you through the wet and latches for one heart, drops
|
||||
off and cannot latch again for a moment (a hit breaks it up); the
|
||||
**will-o'-wisp**, whose light draws every monster within ten units of it
|
||||
toward you at a fifth more speed until a shot puts it out (it stays dim for
|
||||
six seconds, glows where it will return and then burns again); and the **bog
|
||||
body**, which climbs out of the mud harmless and then shambles. The **Harpoon**
|
||||
is the stage's own weapon (a double tap): it pierces everything in its line
|
||||
and is the one shot that reaches a lurker's eyes under the water. **The Bog
|
||||
Runner** is a fan-boat skim down a black channel with a swarm of leeches
|
||||
boiling up in your wake: switch between the open channel and the mud flats at
|
||||
the banks, jump snags and cypress knees, duck moss veils and low limbs, and
|
||||
shoot the hag's charms and the gas pockets (a pocket's burst pushes the swarm
|
||||
back). Easing off, the mud flats and a fan clogged with mud let the swarm
|
||||
gain, and at your heels it takes a heart. Like the other rides it plays for five
|
||||
hearts of its own and ends with three to nine Lucky Dice. The boss is **Old
|
||||
Mother Bog**, who keeps her distance along the planks: she sends a low wave
|
||||
of mud to jump, or spits from her cauldron to leave a muck patch that burns
|
||||
for three seconds (it shows where it will land first). Late in each rest her
|
||||
cauldron opens, and a shot into it counts triple. At half her health she goes
|
||||
under, bubbles show where she will come up near you, and she fights on with
|
||||
shorter waits and a second patch aimed ahead of your feet.
|
||||
Not every room is dark: each time you enter one it is dark three times in
|
||||
five and otherwise lit, dim but seen whole (the same for the same run's
|
||||
seed). In a dark room only half as many monsters come in from the edge
|
||||
seed). The Long Hall, where every run starts, is always lit until you take
|
||||
its key, and then the lights go out for the rest of the room. In a dark
|
||||
room only half as many monsters come in from the edge
|
||||
behind you. Power-ups lie in the rooms and now and then drop from
|
||||
a kill: **Spread shot** and **Rapid fire** (eight seconds each), a **Garlic
|
||||
shield** (shrugs off one hit and sees off what touched you; lose a life
|
||||
@@ -1365,9 +1470,9 @@ building rather than asking, so the page shows the build instead:
|
||||
within the phase, to match the bar — the phase is already named in the
|
||||
headline — so you never see "Task 4.2 of 6"; the page rewrites that form if
|
||||
an agent still sends it.
|
||||
- **The phase's task list** in its own tab, ticking as each task lands on
|
||||
disk, and **the phase file itself** (`phase-3.md`) rendered in the next —
|
||||
the prerequisites and task specs, not just the checklist.
|
||||
- **The phase file itself** (`phase-3.md`) in its own tab: the
|
||||
prerequisites and every task in full, each one ticking as it lands on
|
||||
disk.
|
||||
- **Any question the build needs answered** (which phase, a spec conflict,
|
||||
failing tests) appears as an ordinary question, and the sign-off is a
|
||||
**Completion report** tab with an *Approve this phase* card.
|
||||
@@ -1587,9 +1692,9 @@ On Appearance and Sounds & activities each change saves the moment you make it,
|
||||
|
||||
### Agents & models
|
||||
|
||||
Most people never need this tab: Plan2Code finds the agents installed on the machine and ships an up-to-date model list with every release. It opens on a summary table, one row per agent with its models and whether its command was found on this machine. **Edit** opens that agent's form and **Add agent** a blank one. Nothing on this tab saves as you type: each form has its own **Save** and **Discard**, and shows an **Unsaved** badge while it holds a change. Leaving a form with an unsaved change (another tab, **Back to summary**, **Close**, `Esc`) asks first: save it, discard it, or keep editing. Saving one agent never sends another's half-typed edit.
|
||||
Most people never need this tab: Plan2Code finds the agents installed on the machine and ships an up-to-date model list with every release. It opens on a list of agents on the left, one row per agent with its models and whether its command was found on this machine. Picking a row opens that agent's form in the pane beside it, and **Add agent** a blank one. Under the list, **Or start from a template** offers the same starter templates the setup page has (GitHub Copilot CLI, OpenCode, Gemini CLI, Pi): picking one shows its note and **Use this template**, which opens the new-agent form prefilled rather than saving anything behind your back. Nothing on this tab saves as you type: each form has its own **Save** and **Discard**, and shows an **Unsaved** badge while it holds a change. Leaving a form with an unsaved change (another tab, picking another agent, **Close**, `Esc`) asks first: save it, discard it, or keep editing. Saving one agent never sends another's half-typed edit.
|
||||
|
||||
**Models.** The `plan2code` launcher's model menu comes from `models.json`, which every install overwrites with the authors' curated list. Each built-in agent's form (Claude, Devin, Codex) shows that list under *Comes with Plan2Code*, and below it **Models you added**, each a model id and the name shown in the menu, for a model that came out before Plan2Code was updated. Additions are kept in `~/.plan2code/models.json` and survive updates, unless the curated list now includes them; **Remove** takes one out. Restart `plan2code` to see a change. You can always run `plan2code --model <id>`, or switch model inside your agent before running a skill. Devin ids ending `-xhigh` or `-max` are refused. Maintainers refresh the curated list with the repo-local `/plan2code-model-update` skill, which shows a diff and changes only what they approve.
|
||||
**Models.** The `plan2code` launcher's model menu comes from `models.json`, which every install overwrites with the authors' curated list. Each built-in agent's form (Claude, Devin, Codex) shows that list under *Comes with Plan2Code*, and below it **Models you added**, each a model id and the name shown in the menu, for a model that came out before Plan2Code was updated. Additions are kept in `~/.plan2code/models.json` and survive updates, unless the curated list now includes them; **Remove** takes one out. Restart `plan2code` to see a change. You can always run `plan2code --model <id>`, or switch model inside your agent before running a skill. Devin ids ending `-xhigh` or `-max` are refused. Maintainers refresh the curated list, and the shipped agent list's install data, with the repo-local `/plan2code-launcher-update` skill, which shows a diff and changes only what they approve.
|
||||
|
||||
**Agents.** An agent you add is an agent CLI Plan2Code did not find on its own, which the `plan2code` command and the desktop app can then start. Each one has a name, the command to run (a bare name looked up on `PATH`, or a full path), and optional fields:
|
||||
|
||||
@@ -1660,6 +1765,21 @@ the idle clock never runs down while you are there. Close the tab and it shuts
|
||||
itself down about two minutes later; it stops after four hours regardless, and
|
||||
the agent stops it outright when the session ends.
|
||||
|
||||
**The setup session hands its tab to the agent it finds.** A `setup` session is
|
||||
agent-less: nothing reads its sends, so the page's agent-silence and question
|
||||
rules are switched off and only the idle deadline ends it. The `plan2code`
|
||||
launcher started the session and polls it for a pick; **Start with this agent**
|
||||
posts an `__start` action the launcher collects, and it spawns that agent with
|
||||
two environment variables, `PLAN2CODE_SETUP_ANNOUNCE` (the setup server's
|
||||
address) and `PLAN2CODE_SETUP_TOKEN` (a per-session token). The new agent's own
|
||||
`open` then POSTs its sign-in URL to `POST /handover` on the setup server
|
||||
instead of opening a browser; the token guards the route, the setup page gets a
|
||||
`move` event on its `/events` stream carrying the URL, and the tab follows it
|
||||
onto the new session. Inside the desktop app none of this runs: `open` finds no
|
||||
setup variables (the launcher scrubs the app ones from the setup console it
|
||||
starts), the page tells the app `agent-found` instead, and the app closes the
|
||||
setup page and picks the agent itself.
|
||||
|
||||
That also means **the server routinely outlives the agent**. It is the agent, not
|
||||
the server, that reads your answers, and the two fail separately. The page tells
|
||||
the two apart: the **?** button at the top right opens Help, whose *What this
|
||||
@@ -1783,6 +1903,11 @@ origin.
|
||||
| `POST /notepad/tab/sent` | `{ id, workflow, spec? }`. Records that the tab was sent (`workflow` one of `pathfinder`, `plan`, `quick-task`, `revise-plan`; `spec` like `specs/<name>`) as `sent: { workflow, spec?, at }` on its `tabs.json` entry, shown back in `GET /notepad`'s `tabs`. The page posts it only after the Send that carried the filled box; 400 `bad-sent`, 404 `no-such-tab`. |
|
||||
| `GET /notepad/images/<tab>/<uuid>.jpg`, `<uuid>.thumb.jpg` | Serves a picture or its thumbnail as `image/jpeg`, only by a tab id and a UUID name, a regular file (never a link) whose real path stays inside `~/.plan2code/notepads/`; anything else is 404. |
|
||||
| `POST /subagents` | `{ on, instruction, max }` (`instruction: null` for the shipped default). Saves the switch for this project and skill and answers `{ ok, setting }`; 400 `not-offered` on a skill without the switch, `bad`, `too-long` (over 2,000 characters) or `max` (outside 1 to 20). |
|
||||
| `GET /agents` | The agents view's data: your custom agents and the shipped built-ins and templates, each entry merged with its lookup result `{ state, path, where, folder }`: `state` is `found` (on PATH), `outside` (saved Windows PATH, npm's global folder or an install folder) or `missing`, and `where` says which search found it. Built-ins carry their `install` lines for the server's OS only. |
|
||||
| `POST /agents` | `{ agents, replace? }`. Saves the custom-agent list to `~/.plan2code/agents.json`, validated first (400 `{ error, index, field }`); 409 while the file holds entries `GET /agents` could not read, unless `replace: true`. |
|
||||
| `POST /agents/test` | `{ command }`. Where a command would run from (`{ found, path }`), for the form's Test button; never runs it. |
|
||||
| `POST /agents/use-path` | `{ id }`. "Use it from here": saves the location the lookup found off PATH as the agent's `command` (a built-in becomes a new custom entry; 404 unknown, 409 `not-found`). |
|
||||
| `POST /handover` | Setup sessions only, and only with the session's setup token in `x-plan2code-token`: the new agent's `open` posts `{ url }` here, the server broadcasts a `move` event with it and the setup tab follows. 409 `moved` once it has happened. |
|
||||
|
||||
## For maintainers
|
||||
|
||||
|
||||
@@ -36,7 +36,9 @@ Details: [Architecture](./.agents-docs/AGENTS-architecture.md) (see Status Line
|
||||
|
||||
## Web Console
|
||||
|
||||
Optional local browser UI (`src/web-console/`, zero dependencies, detached `node` server on `127.0.0.1`) bundled into every skill via `additionalReferences`. The bare `plan2code` skill opens its dashboard, a card menu that launches any skill in the same session. Pages cover questions, sign-off gates (with an in-page code review), build progress, the living document, an **Ask** chat, a read-only **Workspace** of extra folders (remembered per folder and spec in `~/.plan2code/console/workspaces.json`), a session meter, a **git board** for the `git` workflow (three tabs, Changes, Branches and Sync, opening on the likely next step; branches, pull, push, commits and pull-request links, drawn from `state.git`; contract in `notes/git.md`), **Stop with a handoff** (handoffs live in `~/.plan2code/handoffs/`, owned by `handoffs.mjs`, swept after 30 days, and offered as dashboard chips to pick up in the same session), a private **Notebook** in the top bar (named tabs of Markdown and pictures, a live-preview CodeMirror editor, one notepad per folder in `~/.plan2code/notepads/`, owned by `notepads.mjs`, private: the agent reads a tab only when you start Pathfinder, Plan, Quick Task or Revise plan from the dashboard with it and send the box it fills (an idea box marked `fill: "note"`, up to five ticked pictures attached), which then marks the tab sent via `POST /notepad/tab/sent`; the agent CLI never imports the store; removed only through Cleanup once a month untouched), **Activities** behind the top bar's die (twelve small games, Snake, Mini golf, Light Trails, Bug Hunt, Sunset Drive, Stack Deploy, Bumper Ring, Rapids Run, Hot Potato, Crossing Rush, Bounce Road and Ghoul Rush, listed in `public/activities.js` with one module per game under `public/activities/` and a card line (`blurb`) each, a picker page of game cards once two are listed that plays one game at a time (another pick drops the last game's round), driven by `screens/activities.js` (keys, key releases for a game with `release()`, canvas pointer events for a game with `pointer()`, one frame timer), paused whenever the person's turn comes and resumed only by the person (while that pause's banner is up, only by its **Unpause game** button), best scores in flat `activityBest<Id>` keys in `looks.json` (lowest wins for a game that sets `lowerIsBetter`; Mini golf opens on a dashboard of its six 18-hole courses, one file each under `public/activities/golf-course-<id>.js`, and keeps a best per course, `activityBestGolf<Course>`), and one number a game may keep between sessions in `activityMemo<Id>` (Snake's tally of surprises found, Light Trails' furthest arena, Bug Hunt's tally of finds, Sunset Drive's roads found, Stack Deploy's highest floor, Bumper Ring's furthest arena, Rapids Run's furthest dam, Hot Potato's furthest venue, Crossing Rush's furthest zone, Bounce Road's furthest stage, Ghoul Rush's most stages cleared in a run), never shown to the agent), a built-in 20-topic Help, the app-only **Implementation Loop** (a dashboard card and a setup screen drawn by the page, `public/screens/loop-setup.js`; the last setup remembered per project in `~/.plan2code/console/loop-setup.json`, owned by `loop-setup.mjs`; a page that locks while `state.loop.driving` is set, until the app posts `loopEnd`; a skill run with `--loop` reports a `loopOutcome` instead of asking for sign-off, per `notes/loop.md`), a first-run Welcome, User Preferences (gear: four tabs, Appearance, Agents & models, System and Sounds & activities, on the `public/tabs.js` helper Help also uses, with `public/prefs.js`, `screens/prefs-dialog.js` and `screens/agents-view.js`) and a bug/idea link to GitHub issues. On opted-in skills (every workflow but the dashboard, Finalize, Changelog, Git and Handoff) a **Subagents** button in the top bar turns helpers on or off per project and skill (on by default for those skills until switched off, saved in `~/.plan2code/console/subagents.json`), and a Helper strength choice (Balanced, Thrifty, Best, Match my session; rules in `src/shared-references/helper-strength.md`, shipped in the twelve helper skills); the agent hears of it as a standing instruction only when it changes, and reports its helpers in a **Subagents** tab beside Ask (contract in `console-subagents.md`). Per-skill facts live in one list, `public/skills.js`, from which the meter, the resume command, Help's card list and the CLI's workflow list are derived; task files are read through `spec-files.mjs` (shared with the `specs.mjs` skill script), and the rule for which hops start the page clean is `startsClean()` in `public/hops.js`. The agent contract is a card plus pointers: `console.md` (the card) once per conversation, then a topic file (`console-*.md` such as `console-docs.md`, `notes/<workflow>.md`, `building*.md`) only when the console names it in its own `read` output, once per session per topic (remembered in `pointers.json` in the session folder, owned by `pointers.mjs`); the console refuses thLine truncated
|
||||
Optional local browser UI (`src/web-console/`, zero dependencies, detached `node` server on `127.0.0.1`) bundled into every skill via `additionalReferences`. The bare `plan2code` skill opens its dashboard, a card menu that launches any skill in the same session. Pages cover questions, sign-off gates (with an in-page code review), build progress, the living document, an **Ask** chat, a read-only **Workspace** of extra folders (remembered per folder and spec in `~/.plan2code/console/workspaces.json`), a session meter, a **git board** for the `git` workflow (three tabs, Changes, Branches and Sync, opening on the likely next step; branches, pull, push, commits and pull-request links, drawn from `state.git`; contract in `notes/git.md`), **Stop with a handoff** (handoffs live in `~/.plan2code/handoffs/`, owned by `handoffs.mjs`, swept after 30 days, and offered as dashboard chips to pick up in the same session), a private **Notebook** in the top bar (named tabs of Markdown and pictures, a live-preview CodeMirror editor, one notepad per folder in `~/.plan2code/notepads/`, owned by `notepads.mjs`, private: the agent reads a tab only when you start Pathfinder, Plan, Quick Task or Revise plan from the dashboard with it and send the box it fills (an idea box marked `fill: "note"`, up to five ticked pictures attached), which then marks the tab sent via `POST /notepad/tab/sent`; the agent CLI never imports the store; removed only through Cleanup once a month untouched), **Activities** behind the top bar's die (twelve small games, Snake, Mini golf, Light Trails, Bug Hunt, Sunset Drive, Stack Deploy, Bumper Ring, Rapids Run, Hot Potato, Crossing Rush, Bounce Road and Ghoul Rush, listed in `public/activities.js` with one module per game under `public/activities/` and a card line (`blurb`) each, a picker page of game cards once two are listed that plays one game at a time (another pick drops the last game's round), driven by `screens/activities.js` (keys, key releases for a game with `release()`, canvas pointer events for a game with `pointer()`, one frame timer), paused whenever the person's turn comes and resumed only by the person (while that pause's banner is up, only by its **Unpause game** button), best scores in flat `activityBest<Id>` keys in `looks.json` (lowest wins for a game that sets `lowerIsBetter`; Mini golf opens on a dashboard of its six 18-hole courses, one file each under `public/activities/golf-course-<id>.js`, and keeps a best per course, `activityBestGolf<Course>`), and one number a game may keep between sessions in `activityMemo<Id>` (Snake's tally of surprises found, Light Trails' furthest arena, Bug Hunt's tally of finds, Sunset Drive's roads found, Stack Deploy's highest floor, Bumper Ring's furthest arena, Rapids Run's furthest dam, Hot Potato's furthest venue, Crossing Rush's furthest zone, Bounce Road's furthest stage, Ghoul Rush's most stages cleared in a run), never shown to the agent), a built-in 20-topic Help, the app-only **Implementation Loop** (a dashboard card and a setup screen drawn by the page, `public/screens/loop-setup.js`; the last setup remembered per project in `~/.plan2code/console/loop-setup.json`, owned by `loop-setup.mjs`; a page that locks while `state.loop.driving` is set, until the app posts `loopEnd`; a skill run with `--loop` reports a `loopOutcome` instead of asking for sign-off, per `notes/loop.md`), a first-run Welcome, User Preferences (gear: four tabs, Appearance, Agents & models, System and Sounds & activities, on the `public/tabs.js` helper Help also uses, with `public/prefs.js`, `screens/prefs-dialog.js` and `screens/agents-view.js`), an agent-less **setup** page (the `setup` workflow `plan2code` or the desktop app opens when no agent can run: each built-in's found / outside-PATH / missing state from `agent-lookup.mjs`, install lines, Check again, Use it from here, starter templates and Start, which hands the tab to the new agent through a token-guarded `POST /handover` and a `move` event; the app shows it in its window from a Set up an agent button instead) and a bug/idea link to GitHub issues. On opted-in skills (every workflow but the dashboard, Finalize, Changelog, Git and Handoff) a **Subagents** button in the top bar turns helpers on or off per project and skill (on by default for those skills until switched off, saved in `~/.plan2code/console/subagents.json`), and a Helper strength choice (Balanced, Thrifty, Best, Match my session; rules in `src/shared-references/helper-strength.md`, shipped in the twelve helper skills); the agent hears of it as a standing instruction only when it changes, and reports its helpers in a **Subagents** tab beside Ask (contract in `console-subagents.md`). Per-skill facts live in one list, `public/skills.js`, from which the meter, the resume command, Help's card list and the CLI's workflow list are derived; task files are read through `spec-files.mjs` (shared with the `specs.mjs` skill script), and the rule for which hops startLine truncated
|
||||
|
||||
One agent list and one lookup rule serve the launcher, the console and the app: `src/launcher/agents.json` (the built-ins and starter templates with per-OS install data) and `src/web-console/agent-lookup.mjs` (`loadAgentList()` and `findAgent()`, both copied by `install.js` into `~/.plan2code/bin/`); the app carries a Rust twin held to the same cases by `scripts/fixtures/agent-lookup-cases.json`.
|
||||
Building or changing an Activities game: follow the game rules in [Architecture](./.agents-docs/AGENTS-architecture.md) ("Building an Activities game": lives in the solid lives pill, the endless-lives code (`cheat(on)`) in every game with lives, banners placed away from the player and see-through over what matters, pausing left to the window).
|
||||
Details: [Architecture](./.agents-docs/AGENTS-architecture.md) (see Web Console section) and [.readme/web-console.md](./.readme/web-console.md)
|
||||
Why the agent-facing console docs are shaped as they are (the card, pointers, refusals): [Web Console Contract](./.agents-docs/AGENTS-web-console-contract.md); it never ships.
|
||||
|
||||
+9
-12
@@ -2,18 +2,6 @@
|
||||
|
||||
All notable changes to Plan2Code will be documented in this file.
|
||||
|
||||
## v4.0.0
|
||||
|
||||
### 💥 Breaking
|
||||
|
||||
- **the `plan2code-loop` CLI is no longer an install target, and the package is removed.** The `plan2code-loop/` directory is deleted, and with it the installer's `O. LOOP CLI` advanced option and the loop's install, update and uninstall wiring. Its docs (`.readme/autonomous-loop.md`, `.agents-docs/AGENTS-plan2code-loop.md`) are gone too, and every remaining mention across the docs, templates, metadata and comments is removed or reworded. The desktop app's **Implementation Loop**, which superseded the CLI, is a separate feature built into the app and is unchanged.
|
||||
|
||||
**Stale installs are still cleaned up.** `install.js` keeps a small `removeLegacyLoopShims()` step that removes the old global artifacts (`plan2code-loop`, `plan2code-loop.cmd`, `plan2code-loop.ps1` and `node_modules/plan2code-loop` under the npm prefix) when they are present. `update()` runs it once before reinstalling and quietly skips a stale `"loop"` entry in `~/.plan2code/install.json`; uninstall runs it too.
|
||||
|
||||
### 🐛 Fixed
|
||||
|
||||
- **desktop app**: the Implementation Loop's end screen offers **Back to the dashboard** next to its other actions, on a finished loop and a stopped one, and it works with no agent running (it opens a fresh dashboard console session in the frame). The screen's status line also tells the truth now: it reads "Loop finished. Pick what happens next." (or "The loop stopped.") as your move instead of spinning "Starting Building + review…", so the taskbar dot goes green there instead of staying dark while the loop's finished page waits.
|
||||
|
||||
## v3.0.0
|
||||
|
||||
### ✨ Added
|
||||
@@ -67,6 +55,13 @@ All notable changes to Plan2Code will be documented in this file.
|
||||
- **web console**: a one-answer question (a pick-one list, or a menu) now has a **Clear** button under its options that takes the card back to how it arrived: no pick, and nothing in **Something else**. A radio pick cannot be unticked by clicking it again, so before this a stray pick could only be swapped for another. The button shows only while the answer has not been sent.
|
||||
|
||||
- **contributors**: `npm run play` opens the web console straight from `src/` with the server reading each page file fresh, so a change to an Activities game shows on the next page reload, without `npm run build:skills` or a reinstall.
|
||||
- **first run**: when no agent CLI can be used (a fresh install, an agent installed but off PATH, the only agent gone after an uninstall, or `--cli` naming a missing agent), the `plan2code` command and the desktop app show one **setup page**: the web console running an agent-less `setup` workflow. It lists each built-in agent (Claude Code, Devin, Codex) as **found**, **found outside PATH** or **not found**, with install commands for your OS, an install page link and **Check again**, plus four starter templates (Pi, Gemini CLI, OpenCode, GitHub Copilot CLI). **Use it from here** makes an off-PATH agent usable without a restart; once an agent is found the run carries straight on, the same browser tab (or the app's launch card) picking up where it left off. With no window or no person, the command prints the install steps and exits 127. One shared agent list (`src/launcher/agents.json`, installed to `~/.plan2code/bin/`) and one lookup rule (`agent-lookup.mjs`, with a Rust twin in the app held to the same fixture cases) serve the launcher, the console and the app; the maintainer skill `plan2code-model-update` is now `plan2code-launcher-update` and re-checks the list's install data too.
|
||||
|
||||
### 💥 Breaking
|
||||
|
||||
- **the `plan2code-loop` CLI is no longer an install target, and the package is removed.** The `plan2code-loop/` directory is deleted, and with it the installer's `O. LOOP CLI` advanced option and the loop's install, update and uninstall wiring. Its docs (`.readme/autonomous-loop.md`, `.agents-docs/AGENTS-plan2code-loop.md`) are gone too, and every remaining mention across the docs, templates, metadata and comments is removed or reworded. The desktop app's **Implementation Loop**, which superseded the CLI, is a separate feature built into the app and is unchanged.
|
||||
|
||||
**Stale installs are still cleaned up.** `install.js` keeps a small `removeLegacyLoopShims()` step that removes the old global artifacts (`plan2code-loop`, `plan2code-loop.cmd`, `plan2code-loop.ps1` and `node_modules/plan2code-loop` under the npm prefix) when they are present. `update()` runs it once before reinstalling and quietly skips a stale `"loop"` entry in `~/.plan2code/install.json`; uninstall runs it too.
|
||||
|
||||
### 🔧 Changed
|
||||
|
||||
@@ -96,6 +91,7 @@ All notable changes to Plan2Code will be documented in this file.
|
||||
- **desktop app**: the top bar's buttons now look like the console's own: rounded, quiet until hovered, then in your highlight color from User Preferences (the app keeps it for the next launch), with **New Session** outlined in it as the likely next step.
|
||||
- **desktop app**: the New Session confirmation shows Planny, drawn like the console's own (outlined shell, star eye, smile), holding a steaming cup of coffee, and its buttons use the console's style: **New Session** in your highlight color, **Cancel** a plain button. The same highlight applies to the panel's other one-button prompts, such as **Retry** and **Reconnect the console**.
|
||||
- **desktop app**: the top bar is rebuilt around two menus and one next step. The project shows as its folder name, with the full path and **Change project** in its menu; **New Session** always sits just left of the agent's menu, which carries a state dot, an amber **checks off** badge in place of the "Permission checks are off for ..." sentence, and **Change agent** once the agent has ended. The console's and the skills' messages share one slot at the right end that shows the most pressing step with its button (**Reconnect the console**, **Update skills**) and "+N more" for the rest, so the bar no longer overflows when several things go wrong at once. The repeated "Plan2Code" label, the full path, the "agent:" prefix and the long "Nothing starts until you press New Session" line are gone.
|
||||
- **web console**: **User Preferences → Agents & models** is rebuilt as a master-detail split: the agent list stays pinned on the left and picking a row opens that agent's form in the pane beside it, so moving between agents no longer goes through a summary-to-form round trip. The same split carries the agent-less setup page (pick list left, state and way forward right). Behind it `agents-view.js` is split into a `screens/agents/` component set (data, list editor, summary, form) behind the unchanged `mountAgentsView` API, and the agent styles live in their own `styles/agents.css`. The setup page's starter templates are offered on the tab too, under **Or start from a template**: **Use this template** opens the new-agent form prefilled. Every capability is kept: per-form Save and Discard, the Unsaved prompt, Test, Delete, the 409 Save anyway path, and the setup states and templates. The Preferences dialog itself now follows the Card width pick, never wider than the wide preset (1080px), instead of a fixed 880px.
|
||||
|
||||
### 🐛 Fixed
|
||||
|
||||
@@ -109,6 +105,7 @@ All notable changes to Plan2Code will be documented in this file.
|
||||
- **web console**: a failed Send says why: the lost-contact state and its reconnect help at once when the console is gone, the console's reason when it refuses the send, or that the console is still up and Send can be pressed again.
|
||||
- **desktop app**: a test console started inside the app (for example by `cargo test` during a build) can no longer take over the window. Before, the window followed it, then fell back to an empty dashboard once the test shut it down, and the build's question sat on a page no one could see. The app now ignores any page whose session is not in its own console store.
|
||||
- **desktop app**: a console too busy to answer a health check in time (a machine running a test suite) is given a second, longer look and then resumed on the same session. It is no longer swapped for a fresh, empty dashboard mid-build.
|
||||
- **desktop app**: the Implementation Loop's end screen offers **Back to the dashboard** next to its other actions, on a finished loop and a stopped one, and it works with no agent running (it opens a fresh dashboard console session in the frame). The screen's status line also tells the truth now: it reads "Loop finished. Pick what happens next." (or "The loop stopped.") as your move instead of spinning "Starting Building + review…", so the taskbar dot goes green there instead of staying dark while the loop's finished page waits.
|
||||
|
||||
## v2.11.1
|
||||
|
||||
|
||||
+1
-1
@@ -5,7 +5,7 @@
|
||||
- **Node.js 18 or newer.** Check with `node --version`. No Node? Get it from [nodejs.org](https://nodejs.org/) (the LTS download), or run `winget install OpenJS.NodeJS.LTS` on Windows, `brew install node` on macOS, or use `nvm` on Linux. Then open a new terminal.
|
||||
- **Start from your project.** Open your terminal in the project you want to work on (`cd` into it) before you run anything. Plan2Code works on the folder you start it in.
|
||||
- **Ways in.** `plan2code` (Claude Code, Devin or Codex), or type `/plan2code` in your agent (`$plan2code` in Codex).
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first.
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first, or let the `plan2code` command's setup page walk you through it.
|
||||
|
||||
## Launch
|
||||
|
||||
|
||||
@@ -35,7 +35,7 @@ The dashboard, in a project halfway through a build. It suggests the next step f
|
||||
- **Node.js 18 or newer.** Check with `node --version`. No Node? Get it from [nodejs.org](https://nodejs.org/) (the LTS download), or run `winget install OpenJS.NodeJS.LTS` on Windows, `brew install node` on macOS, or use `nvm` on Linux. Then open a new terminal.
|
||||
- **Start from your project.** Open your terminal in the project you want to work on (`cd` into it) before you run anything. Plan2Code works on the folder you start it in.
|
||||
- **Ways in.** `plan2code` (Claude Code, Devin or Codex), or type `/plan2code` in your agent (`$plan2code` in Codex).
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first.
|
||||
- **No agent yet?** Install Claude Code, Codex or Devin first, or let the `plan2code` command's setup page walk you through it.
|
||||
|
||||
Installation needs network access and runs through the [skills CLI](https://skills.sh). To update, run `plan2code update` (or re-run the install command).
|
||||
|
||||
@@ -92,12 +92,22 @@ which opens a folder picker first. Uninstalling (`U`) removes both.
|
||||
<details>
|
||||
<summary>Using another agent CLI, or none yet</summary>
|
||||
|
||||
Plan2Code runs inside an AI coding agent CLI. If `plan2code` finds none of Claude Code, Devin or Codex on
|
||||
your `PATH`, it says so and prints each one's install command and official page, then exits; the desktop app
|
||||
shows the same help in a panel with an **Install page** link per agent and a **Check again** button, so you
|
||||
can install one and carry on without restarting.
|
||||
Plan2Code runs inside an AI coding agent CLI. With no agent it can run (none of Claude Code,
|
||||
Devin or Codex, and no working custom agent),
|
||||
`plan2code` opens a setup page in your browser (the web console runs it, so no agent is needed).
|
||||
The page lists each agent as **Found**, **Found outside PATH** or **Not found**, with its install
|
||||
commands for your system, a Copy button per command and an **Install page** link. Install one and
|
||||
press **Check again**: no restart needed. An agent found outside `PATH` gets **Use it from here**,
|
||||
which saves where it was found so you never touch `PATH` yourself. Below the list sit four starter
|
||||
templates (GitHub Copilot CLI, OpenCode, Gemini CLI and Pi) for agents Plan2Code does not ship.
|
||||
**Start with this agent** carries the run straight on in the same tab, onto the new agent's
|
||||
dashboard. Naming a built-in that is missing with `--cli <name>` opens the same page on that agent
|
||||
(a missing custom agent prints its own steps and exits 127). In the
|
||||
desktop app a **Set up an agent** button opens the same page in the window and returns to the
|
||||
launch card with the found agent picked. Where no page can open, such as over SSH or with no
|
||||
display, `plan2code` prints the install commands and install pages and exits with code 127.
|
||||
|
||||
To use a different agent CLI, open the web console's **User Preferences → Agents & models** and add it: a name, the
|
||||
Once an agent is running, to use a different agent CLI, open the web console's **User Preferences → Agents & models** and add it: a name, the
|
||||
command, and (optionally) its arguments, the start prompt, arguments for skipping permission prompts, and
|
||||
how it takes a model. Custom agents are saved in `~/.plan2code/agents.json` and used by both the
|
||||
`plan2code` command (listed after the built-ins; `--cli <id>` picks one) and the desktop app's picker. The
|
||||
|
||||
+9
-3
@@ -74,9 +74,15 @@ you picked, and reuses the same agent); a CLI the app cannot find is named, with
|
||||
instead of just being grayed out. The card is skipped when the launcher already passed an agent to
|
||||
start.
|
||||
|
||||
With no agent installed at all, the checklist and the launch card explain what an agent CLI is and
|
||||
show each built-in's install command with an **Install page** link. Install one (or add a custom
|
||||
agent) and press **Check again**: the app finds it without a restart.
|
||||
With no agent installed at all, the checklist and the launch card each show a **Set up an agent**
|
||||
button. It opens the same setup page the `plan2code` command uses, inside the app's window: every
|
||||
built-in listed as found, found outside PATH or not found, with its install commands for your
|
||||
system, an **Install page** link, **Check again**, **Use it from here** for one found outside
|
||||
PATH, and the starter templates for other agent CLIs. When the page reports an agent found, the
|
||||
app returns to where it was (the checklist or the launch card), re-checks, and picks that agent on
|
||||
the launch card ready for Start. A **Back** button leaves the page at any time. When the saved
|
||||
(last used) agent is gone but another works, a one-line notice on the launch card says so and the
|
||||
card carries on with the working one.
|
||||
|
||||
The window's own title (and so its taskbar entry) reads **Plan2Code - <folder name>** once a
|
||||
project is open, so two or more windows on different projects read apart without opening each one
|
||||
|
||||
+2
-2
@@ -226,7 +226,7 @@ footer a { color: inherit; }
|
||||
<li><strong>Node.js 18 or newer.</strong> Check with <code>node --version</code>. No Node? Get it from <a href="https://nodejs.org/">nodejs.org</a> (the LTS download), or run <code>winget install OpenJS.NodeJS.LTS</code> on Windows, <code>brew install node</code> on macOS, or use <code>nvm</code> on Linux. Then open a new terminal.</li>
|
||||
<li><strong>Start from your project.</strong> Open your terminal in the project you want to work on (<code>cd</code> into it) before you run anything. Plan2Code works on the folder you start it in.</li>
|
||||
<li><strong>Ways in.</strong> <code>plan2code</code> (Claude Code, Devin or Codex), or type <code>/plan2code</code> in your agent (<code>$plan2code</code> in Codex).</li>
|
||||
<li><strong>No agent yet?</strong> Install Claude Code, Codex or Devin first.</li>
|
||||
<li><strong>No agent yet?</strong> Install Claude Code, Codex or Devin first, or let the <code>plan2code</code> command's setup page walk you through it.</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="cmd">
|
||||
@@ -401,7 +401,7 @@ footer a { color: inherit; }
|
||||
<li><strong>Node.js 18 or newer.</strong> Check with <code>node --version</code>. No Node? Get it from <a href="https://nodejs.org/">nodejs.org</a> (the LTS download), or run <code>winget install OpenJS.NodeJS.LTS</code> on Windows, <code>brew install node</code> on macOS, or use <code>nvm</code> on Linux. Then open a new terminal.</li>
|
||||
<li><strong>Start from your project.</strong> Open your terminal in the project you want to work on (<code>cd</code> into it) before you run anything. Plan2Code works on the folder you start it in.</li>
|
||||
<li><strong>Ways in.</strong> <code>plan2code</code> (Claude Code, Devin or Codex), or type <code>/plan2code</code> in your agent (<code>$plan2code</code> in Codex).</li>
|
||||
<li><strong>No agent yet?</strong> Install Claude Code, Codex or Devin first.</li>
|
||||
<li><strong>No agent yet?</strong> Install Claude Code, Codex or Devin first, or let the <code>plan2code</code> command's setup page walk you through it.</li>
|
||||
</ul>
|
||||
</div>
|
||||
<div class="cmd">
|
||||
|
||||
@@ -6,7 +6,7 @@ The app is optional. The Node web console and the skills never depend on it, so
|
||||
|
||||
## Agents and the taskbar
|
||||
|
||||
**Agent picker.** The launch card lists Claude Code, Devin and Codex, then any custom agents from `~/.plan2code/agents.json` (added in the console's User Preferences → Agents & models, the same list the `plan2code` command uses). The app starts on an agent that is installed (your last pick when it still is), never assumes Claude Code, and a custom agent has no effort row; New Session reuses whichever agent you started. Custom agents offer their own models, and `/plan2code` only does something in an agent that loads the installed Plan2Code skills.
|
||||
**Agent picker.** The launch card lists Claude Code, Devin and Codex, then any custom agents from `~/.plan2code/agents.json` (added in the console's User Preferences → Agents & models, the same list the `plan2code` command uses). The app starts on an agent that is installed (your last pick when it still is), never assumes Claude Code, and a custom agent has no effort row; New Session reuses whichever agent you started. The Model dropdown offers the same list the `plan2code` launcher's model question does (the shipped `models.json` plus anything you added in User Preferences), a custom agent its own `models`, and it hides for an agent with none; `/plan2code` only does something in an agent that loads the installed Plan2Code skills.
|
||||
|
||||
**No agent installed.** The first-run checklist and the launch card show what an agent CLI is, each built-in's install command and an **Install page** link, and a note that other agents are added under Agents. Install one, press **Check again** (the app looks at `PATH` and `agents.json` again), and Start works without restarting the app.
|
||||
|
||||
|
||||
@@ -59,10 +59,11 @@ file directly after checking it against the release's checksum list.
|
||||
- [ ] The first run (no `firstRunDone` saved yet) shows the checklist (Node, an agent CLI, the
|
||||
project folder, the skills version) before the launch card; a later launch goes straight to
|
||||
the launch card
|
||||
- [ ] The launch card offers agent, model, effort (Claude and Codex only) and permission mode
|
||||
(checks off is ticked by default, matching the plain `plan2code` launcher; untick it for
|
||||
an agent that keeps its normal approval prompts); a CLI it could not find is named, not
|
||||
just disabled
|
||||
- [ ] The launch card offers agent, a model dropdown (the same models.json list the `plan2code`
|
||||
launcher asks with, hidden for an agent with no listed models), effort (Claude and Codex
|
||||
only) and permission mode (checks off is ticked by default, matching the plain `plan2code`
|
||||
launcher; untick it for an agent that keeps its normal approval prompts); a CLI it could
|
||||
not find is named, not just disabled
|
||||
- [ ] **Dock the terminal to the right**: the splitter becomes vertical, the toolbar stacks, and the
|
||||
dashboard keeps the rest of the width; dock it back to the bottom
|
||||
- [ ] **Collapse** the terminal to a thin strip (either dock) and **View Agent Terminal** brings it
|
||||
|
||||
Reference in new issue
Block a user