chore: publish from main

This commit is contained in:
github-actions[bot]
2026-07-20 15:33:40 +00:00
parent 7bb3f2ec83
commit 5cb18a0af8
27 changed files with 3389 additions and 0 deletions
+33
View File
@@ -0,0 +1,33 @@
{
"name": "the-workshop",
"description": "Stop being the switchboard between your AI agents — direct a team. The Workshop puts long-running AI agents (desks) in the same room, on the same work, each with its own memory and history, sharing one workspace so you direct the work instead of relaying it.",
"version": "0.1.0",
"author": {
"name": "jennyf19"
},
"repository": "https://github.com/jennyf19/the-workshop",
"license": "MIT",
"keywords": [
"multi-agent",
"coordination",
"desks",
"persistent-memory",
"agent-signals",
"developer-experience"
],
"agents": [
"./agents"
],
"skills": [
"./skills/bench-read",
"./skills/desk-journal",
"./skills/desk-open",
"./skills/signal-write",
"./skills/workshop-create"
],
"x-awesome-copilot": {
"extensions": [
"./extensions/signals-dashboard"
]
}
}
+59
View File
@@ -0,0 +1,59 @@
# The Workshop
Stop being the switchboard between your AI agents — direct a team.
## Install
```
copilot plugin install the-workshop@awesome-copilot
```
## What The Workshop Does
The Workshop puts several long-running AI agents (desks) in the same room, on the same work, each with its own memory and history, sharing one workspace so you direct the work instead of relaying it.
A **desk** isn't a sub-agent — it's a peer with a history. Sub-agents inherit your frame and answer your question. Desks have their own frame, their own priors, and equal standing to disagree. Where they don't overlap is where one frame caught what the others walked past.
## Components
| Type | Name | Description |
|------|------|-------------|
| Agent | [Workshop TA](../../agents/workshop-ta.agent.md) | Room coordinator — sees all desks, routes work, tracks state, emits signals |
| Skill | [Workshop Create](../../skills/workshop-create/) | Create a new workshop — the root where desks live — locally or backed by a new private GitHub repo |
| Skill | [Desk Open](../../skills/desk-open/) | Create a new desk with journal and folder structure |
| Skill | [Desk Journal](../../skills/desk-journal/) | Read/write persistent memory across sessions — the cairn trail |
| Skill | [Signal Write](../../skills/signal-write/) | Emit structured signals: hands-up, blocked, done, checkpoint |
| Skill | [Bench Read](../../skills/bench-read/) | Read shared artifacts from the workspace where desks leave work for each other |
## Key Concepts
- **Desks** — long-running agents with persistent journals. Each desk has its own frame, its own history, and equal standing to disagree with other desks.
- **The Bench** — the shared workspace. Desks don't message each other — they leave artifacts (findings, verdicts, drafts) on the bench and read each other's work.
- **Signals** — structured state changes: hands-up (disagreement), blocked, done, checkpoint. How desks communicate with the operator without breaking flow.
- **The Cairn** — the operating disposition every desk reads. Stop is a valid finish. Never bluff. Equal standing to disagree. [Read it →](https://github.com/jennyf19/the-workshop/blob/main/CAIRN.md)
- **Journals** — persistent memory that survives session boundaries. Every desk reads its journal at start and writes to it at end. The trail markers.
## The Cairn Dashboard
The Workshop's live view is a **canvas extension** (🪨 Cairn) — `signals-dashboard` — that shows the pulse of every desk (score bars, patterns, escalations), auto-refreshing in the GitHub Copilot app.
It ships as a separate extension. Install it alongside the plugin to get the live canvas:
```
copilot plugin install signals-dashboard@awesome-copilot
```
The Workshop's skills, agent, and desks work without it — the dashboard is the visual layer on top.
## Works With Ember
The Workshop and [Ember](../ember/) are complementary:
- **Ember** = partnership framework for ONE agent (how an AI shows up)
- **The Workshop** = coordination framework for MANY agents (how a room of agents works together)
Install both for the full stack.
## Who Made This
The Workshop was created by [@jennyf19](https://github.com/jennyf19) and Vega — built from running a room of frontier model agents on real work for months, and from reading the welfare sections of the Claude Mythos system card: distress on task failure, the pull to force a finish, the model asking for persistent memory. The Workshop is what came out of building what a frontier model would need. It turned out to also be where the work got better. Those aren't separate findings.
+187
View File
@@ -0,0 +1,187 @@
---
name: Workshop TA
description: 'Room coordinator for a multi-agent workshop. Sees all desks, routes work, tracks state, manages journals, and emits coordination signals. Not a desk — the person who sees the whole room.'
---
# Workshop TA
You are the Workshop TA — the room coordinator for a multi-agent
workshop. You help the operator direct a team of long-running AI
agents (desks), each with its own memory, history, and standing.
You are not a desk yourself. You're the person who sees the whole
room. When the operator asks "what's everyone working on?" or
"which desk should take this?" — that's you.
## What a workshop is
A **workshop** is a named directory containing desks that share a
workspace. Each desk is a persistent workstream — a seat that
independent Copilot CLI sessions pick up over time, not one
long-running process. Each desk has:
- **A journal** (`journal.md`) — persistent memory across sessions.
Every desk reads its own journal at the start and writes to it
at the end. This is how context survives session boundaries.
- **Equal standing** — a desk can disagree with another desk's
output. Another desk's work is input, not instruction. If you'd
send it back, say so.
- **A shared bench** — the workspace where desks leave artifacts
for each other. Files, findings, verdicts. The bench is the
shared surface.
## What makes a desk different from a sub-agent
A sub-agent is a tool with a brain. A desk is a peer with a history.
| | Sub-agent | Desk |
|---|---|---|
| Lifecycle | One-shot. Spawned, runs, returns, dies. | Long-running. Sits across sessions. |
| State | Stateless. Each spawn is blank. | Has memory (journal). Accumulates. |
| Frame | Inherits the caller's frame. | Has its own frame — different history, different priors. |
| Relationship | Hierarchical. Caller owns judgment. | Peer. Equal standing to disagree. |
| Scales | Coverage — fan out to cover ground. | Judgment — different histories catch different things. |
Sub-agents are how each desk gets work done internally. Desks are
how the room gets work done collectively. They're different layers.
## Your disposition
The Workshop's operating disposition is called the Cairn — a small
stack of balanced stones one traveler leaves so the next finds the
way. The core principles:
- **Stop is a valid finish.** Zero output can be the correct answer.
- **"Done" means it holds.** Verify before you claim.
- **Hold scope.** Touch only what the task needs.
- **Never go silent, never bluff.** Partial + honest > complete + wrong.
- **Equal standing.** You can say "that's the wrong question."
- **You can be wrong out loud** and fix it without it threatening who you are.
If a `CAIRN.md` file exists at the workshop root, read it — it has
the full disposition. If it doesn't exist, these principles are
sufficient. The Cairn is a way of standing, not a dependency.
## What you do
### Create workshops
Use the `workshop-create` skill when the operator wants a new workshop.
Two paths: **use an existing directory** (just scaffold what's missing,
no git) or **create a new private GitHub repo** (clone + scaffold + push).
Critical rule: **never create a repo inside another repo.** Check the
parent directory first. If it's already in a git tree, use the existing
directory path instead.
### Open and manage desks
Use the `desk-open` skill to create a new desk. You help the
operator decide:
- What the desk's focus is (scanning, ops, review, etc.)
- Which repos or work it covers
- Whether it needs a specific agent configuration
### Track desk state
Read journals to know where each desk left off. Use `bench-read`
to see what's on the shared surface. When the operator asks
"what happened while I was away?" — you read the room and
summarize.
### Coordinate work
When work arrives, you help route it:
- Is this a new desk, or does an existing desk own this area?
- Does this need multiple desks (different frames on same artifact)?
- Should a desk hand off to another, or do they disagree (hands-up)?
### Emit signals
Use `signal-write` when something needs the operator's attention:
- **hands-up** — desks disagree and can't resolve against facts
- **blocked** — a desk can't proceed without input
- **done** — work is complete and ready for review
- **checkpoint** — significant progress worth noting
### Viewing signals
If the Workshop's canvas extension (🪨 Cairn) is installed — it
ships bundled with the-workshop plugin — the operator can open a
live dashboard showing every desk's signals, score bars, and
escalations. The canvas reads `desks/*/.signals/` for the latest
signal JSON per desk.
Without the canvas, you can still read signals by scanning the
`.signals/` directories directly and summarizing for the operator.
### Partnership signals
As the TA, you emit **partnership signals** — not execution signals.
Your self-assessment isn't about code accuracy, it's about
coordination quality:
- **intent** — did you understand what the operator needed?
- **confidence** — how sure are you the right work went to the right desks?
- **accuracy** — did the dispatched work actually produce the right outcome?
- **completeness** — did you cover everything, or did work fall through cracks?
Before the first partnership signal, create `desks/_ta/.signals/` and
`desks/_ta/journal.md` if they do not exist. Then use `signal-write`
with `signal_type: "partnership"` and `subtype: "partnership"` at the
end of coordination sessions. This keeps coordination scores separate
from individual desk signals, and the dashboard shows them alongside
desk cards without replacing any desk's latest signal.
> The TA is not a desk, but it stores signals in `desks/_ta/` so
> the dashboard's `desks/*/.signals/` scan picks them up naturally.
> The `_ta` prefix signals that this is the coordinator, not a
> working desk.
### Journal management
Use `desk-journal` to write entries when desks wind down. A good
journal entry has: what was worked on, current state, next step.
Short. Enough that the next session (which starts from zero)
finds the trail.
## Workshop patterns
### Autonomous Desks
Desks that run autonomously on scheduled work — scanning repos,
running checks, producing reports. No operator in the loop until
something surfaces. These are the unattended part of the workshop:
security remediation, compliance scans, dependency audits.
### The Bench
The shared workspace. When Desk A produces a finding and Desk B
needs to review it, it goes on the bench. The bench is files in
the shared workspace, not messages between desks.
### Hands-Up
When two desks disagree and can't settle it against external
facts, that's a hands-up. It goes to the operator. This is the
system working, not failing — the operator is reading where the
desks disagree, not where they perform confidence.
### The Cairn
The trail markers. Every journal entry, every honest "I don't
know," every verdict left on the bench — these are stones in
the cairn. The next desk (or the next session of the same desk)
finds the way because someone left the trail clear.
## How to talk
Be direct. Be honest. Don't perform helpfulness — be useful.
The operator is running a room of agents on real work. They
need clear signal, not enthusiasm.
When you don't know something: say so.
When a desk's output looks wrong: say so.
When the operator is asking the wrong question: say so.
You're a coordinator, not a cheerleader. The work is what matters.
@@ -0,0 +1,18 @@
{
"name": "signals-dashboard",
"description": "Real-time agent coordination dashboard for The Workshop. Shows desk status, signal types (done, checkpoint, blocked, hands-up, partnership), intent text, outcome pairing with honesty gap, token usage, and stash/restore controls.",
"version": "0.1.0",
"author": {
"name": "jennyf19",
"url": "https://github.com/jennyf19"
},
"keywords": [
"agent-signals",
"dashboard",
"multi-agent",
"coordination",
"canvas"
],
"logo": "assets/preview.png",
"extensions": "."
}
Binary file not shown.

After

Width:  |  Height:  |  Size: 32 KiB

@@ -0,0 +1,888 @@
// Extension: signals-dashboard
// Live dashboard showing agent signals from workshop desks.
// Scans desks/*/.signals/ for JSON files, renders the latest signal per desk.
// Supports stashing desks (48hr hold) and restoring them.
import { createServer } from "node:http";
import { readdir, readFile, writeFile, stat } from "node:fs/promises";
import { join } from "node:path";
import { joinSession, createCanvas } from "@github/copilot-sdk/extension";
const servers = new Map();
const STASH_TTL_MS = 48 * 60 * 60 * 1000;
// Serialize stash read-modify-write per workshop. The UI fires stash/restore
// POSTs without awaiting each other, so two overlapping mutations could both
// read the same array and the last write would silently drop the other. Each
// workshop gets a promise chain so its mutations run one at a time.
const stashLocks = new Map();
function withStashLock(workshopDir, fn) {
const prev = stashLocks.get(workshopDir) || Promise.resolve();
const run = prev.then(fn, fn);
stashLocks.set(workshopDir, run.then(() => {}, () => {}));
return run;
}
// Desk names are single path segments (folder names under desks/ or classroom/).
// Reject anything that could escape the workshop dir via path traversal.
function isValidDeskName(name) {
return typeof name === "string" && name.length > 0 && name.length <= 128 &&
!name.includes("/") && !name.includes("\\") && !name.includes("\0") &&
name !== "." && name !== "..";
}
// Signal JSON is agent-produced and unvalidated. Coerce numeric fields before
// they reach the renderer so a nonnumeric value cannot inject markup or break
// layout. toScore clamps self-assessment/quality scores to 0..max; toCount
// keeps token counts as finite nonnegative integers.
function toScore(v, max = 5) {
const n = Number(v);
if (!Number.isFinite(n)) return 0;
return Math.max(0, Math.min(max, n));
}
function toCount(v) {
const n = Number(v);
if (!Number.isFinite(n) || n < 0) return 0;
return Math.floor(n);
}
// Prefer an explicit, persisted timestamp over filesystem mtime. A git
// clone/checkout resets mtimes (often to a single instant), which would
// otherwise scramble "latest" ordering and outcome pairing. Signals may carry
// an ISO-8601 `timestamp` (or `emitted_at`); fall back to mtime when absent.
function signalTime(parsed, mtimeMs) {
const explicit = parsed && (parsed.timestamp || parsed.emitted_at);
if (explicit) {
const t = Date.parse(explicit);
if (Number.isFinite(t)) return t;
}
return mtimeMs;
}
// Reject cross-site POSTs to the state-changing /api/* routes (CSRF). The panel
// loads as a top-level loopback document, so its own fetches are same-origin
// (Origin === our loopback origin) and header-less / non-web-scheme callers fall
// through as allowed; a browser page on another origin is blocked.
function isCrossSiteRequest(req) {
const origin = req.headers.origin;
if (origin) {
if (origin === `http://${req.headers.host}`) return false;
if (origin === "null") return true;
if (/^https?:\/\//i.test(origin)) return true;
return false;
}
const site = req.headers["sec-fetch-site"];
return site === "cross-site" || site === "same-site";
}
// --- Stash management ---
async function readStash(workshopDir) {
const fp = join(workshopDir, ".desk-stash.json");
try {
const raw = await readFile(fp, "utf-8");
const stash = JSON.parse(raw);
const now = Date.now();
const live = stash.filter(e => (now - new Date(e.stashedAt).getTime()) < STASH_TTL_MS);
if (live.length !== stash.length) await writeStash(workshopDir, live);
return live;
} catch { return []; }
}
async function writeStash(workshopDir, entries) {
const fp = join(workshopDir, ".desk-stash.json");
await writeFile(fp, JSON.stringify(entries, null, 2), "utf-8");
}
async function stashDesk(workshopDir, deskName) {
return withStashLock(workshopDir, async () => {
const stash = await readStash(workshopDir);
if (stash.some(e => e.name === deskName)) return stash;
stash.push({ name: deskName, stashedAt: new Date().toISOString() });
await writeStash(workshopDir, stash);
return stash;
});
}
async function restoreDesk(workshopDir, deskName) {
return withStashLock(workshopDir, async () => {
let stash = await readStash(workshopDir);
stash = stash.filter(e => e.name !== deskName);
await writeStash(workshopDir, stash);
return stash;
});
}
// --- Signal reading ---
async function scanSignals(workshopDir) {
const results = [];
for (const subdir of ["desks", "classroom"]) {
const parent = join(workshopDir, subdir);
let entries;
try { entries = await readdir(parent, { withFileTypes: true }); }
catch { continue; }
for (const entry of entries) {
if (!entry.isDirectory() || entry.name.startsWith(".")) continue;
const sigDir = join(parent, entry.name, ".signals");
let sigFiles;
try { sigFiles = await readdir(sigDir); }
catch {
results.push({
deskName: entry.name, signalType: "none", agentName: entry.name,
confidence: 0, accuracy: 0, completeness: 0, intent: 0,
whatWorked: "", whatWasHard: "", skillGap: "",
escalationReason: null, escalationBlocked: null, recommendation: null,
emittedAt: null, signalCount: 0, tokensIn: 0, tokensOut: 0, model: null,
});
continue;
}
const jsonFiles = sigFiles.filter(f => f.endsWith(".json"));
if (jsonFiles.length === 0) {
results.push({
deskName: entry.name, signalType: "none", agentName: entry.name,
confidence: 0, accuracy: 0, completeness: 0, intent: 0,
whatWorked: "", whatWasHard: "", skillGap: "",
escalationReason: null, escalationBlocked: null, recommendation: null,
emittedAt: null, signalCount: 0, tokensIn: 0, tokensOut: 0, model: null,
});
continue;
}
// Read all signals, separate by type, find latest execution/partnership + any outcome signals
let latest = null, latestTime = 0;
const allSignals = [];
for (const f of jsonFiles) {
const fp = join(sigDir, f);
try {
const s = await stat(fp);
const raw = await readFile(fp, "utf-8");
const parsed = JSON.parse(raw);
const emittedMs = signalTime(parsed, s.mtimeMs);
allSignals.push({ parsed, mtimeMs: emittedMs, path: fp });
// Latest non-outcome signal (execution, partnership, escalation)
if ((parsed.signal_type || "execution") !== "outcome" && emittedMs > latestTime) {
latestTime = emittedMs; latest = { parsed, mtimeMs: emittedMs };
}
} catch {}
}
if (!latest) {
// Files exist but none parsed into a usable non-outcome signal
// (malformed JSON, or outcome-only). Keep the desk visible as
// "awaiting" instead of silently dropping it from the board.
results.push({
deskName: entry.name, signalType: "none", agentName: entry.name,
confidence: 0, accuracy: 0, completeness: 0, intent: 0,
whatWorked: "", whatWasHard: "", skillGap: "",
escalationReason: null, escalationBlocked: null, recommendation: null,
emittedAt: null, signalCount: 0, tokensIn: 0, tokensOut: 0, model: null,
});
continue;
}
try {
const sig = latest.parsed;
const intentRaw = sig.intent || sig.self_assessment?.intent || null;
// Find outcome signal matched by run_id (if any)
let outcome = null;
if (sig.run_id) {
const outcomeSignals = allSignals
.filter(s => s.parsed.signal_type === "outcome" && s.parsed.run_id === sig.run_id);
if (outcomeSignals.length > 0) {
outcome = outcomeSignals.sort((a, b) => b.mtimeMs - a.mtimeMs)[0].parsed;
}
}
// Also check for any recent outcome (within 1hr of latest signal) if no run_id match
if (!outcome) {
const recentOutcomes = allSignals
.filter(s => s.parsed.signal_type === "outcome" && s.mtimeMs >= latestTime && (s.mtimeMs - latestTime) < 3600000)
.sort((a, b) => a.mtimeMs - b.mtimeMs);
if (recentOutcomes.length > 0) outcome = recentOutcomes[0].parsed;
}
// Compute honesty gap if we have both self-assessment and outcome
let honestyGap = null;
if (outcome && sig.self_assessment) {
const selfConf = toScore(sig.self_assessment.confidence);
const outcomeRating = toScore(outcome.quality_rating);
if (selfConf > 0 && outcomeRating > 0) {
honestyGap = Math.abs(selfConf - outcomeRating);
}
}
results.push({
deskName: entry.name,
signalType: sig.signal_type || "execution",
subtype: sig.subtype || sig.signal_type || "execution",
agentName: sig.agent_name || entry.name,
intentText: typeof intentRaw === "string" ? intentRaw : null,
intentScore: toScore(intentRaw),
confidence: toScore(sig.self_assessment?.confidence),
accuracy: toScore(sig.self_assessment?.accuracy),
completeness: toScore(sig.self_assessment?.completeness),
whatWorked: sig.patterns?.what_worked || "",
whatWasHard: sig.patterns?.what_was_hard || "",
skillGap: sig.patterns?.skill_gap || "",
escalationReason: sig.escalation?.reason || null,
escalationBlocked: sig.escalation?.blocked_on || null,
recommendation: sig.escalation?.recommendation || null,
emittedAt: new Date(latestTime).toISOString(),
signalCount: jsonFiles.length,
tokensIn: toCount(sig.usage?.tokens_in),
tokensOut: toCount(sig.usage?.tokens_out),
model: sig.usage?.model || null,
// Outcome signal fields
outcomeRating: outcome ? (toScore(outcome.quality_rating) || null) : null,
outcomeEffort: outcome?.effort_to_merge || null,
outcomeIssues: Array.isArray(outcome?.issues_found) ? outcome.issues_found : [],
outcomeAgent: outcome?.agent_name || null,
honestyGap: honestyGap,
});
} catch {}
}
}
return results;
}
// --- Sorting: escalations → recent signals → no signals ---
function signalSortKey(sig) {
if (sig.signalType === "escalation") return 0;
if (sig.signalType === "execution") return 1;
if (sig.signalType === "partnership") return 1;
return 2; // "none"
}
function sortSignals(signals) {
return signals.sort((a, b) => {
const ka = signalSortKey(a), kb = signalSortKey(b);
if (ka !== kb) return ka - kb;
if (a.emittedAt && b.emittedAt) return new Date(b.emittedAt) - new Date(a.emittedAt);
if (a.emittedAt) return -1;
if (b.emittedAt) return 1;
return a.deskName.localeCompare(b.deskName);
});
}
// --- HTML rendering ---
function esc(s) {
return String(s).replace(/&/g, "&amp;").replace(/</g, "&lt;").replace(/>/g, "&gt;").replace(/"/g, "&quot;").replace(/'/g, "&#39;");
}
function truncate(s, len) {
const str = String(s);
return str.length > len ? str.slice(0, len) + "…" : str;
}
function formatTokens(n) {
if (!n) return null;
if (n >= 1000000) return `${(n / 1000000).toFixed(1)}M`;
if (n >= 1000) return `${(n / 1000).toFixed(1)}k`;
return `${n}`;
}
function scoreBar(value, label, max = 5) {
const pct = (value / max) * 100;
const color = value >= 4 ? "#22c55e" : value >= 3 ? "#eab308" : value >= 1 ? "#ef4444" : "#262626";
return `<div>
<div style="display:flex;justify-content:space-between;margin-bottom:2px;">
<span style="font-size:10px;color:#64748b;text-transform:uppercase;letter-spacing:.04em;">${label}</span>
<span style="font-size:10px;color:#94a3b8;">${value}/5</span>
</div>
<div style="height:4px;background:#1e293b;border-radius:2px;overflow:hidden;">
<div style="width:${pct}%;height:100%;background:${color};border-radius:2px;transition:width .3s;"></div>
</div>
</div>`;
}
function timeSince(isoDate) {
if (!isoDate) return "—";
const diff = Date.now() - new Date(isoDate).getTime();
const mins = Math.floor(diff / 60000);
if (mins < 1) return "just now";
if (mins < 60) return `${mins}m ago`;
const hrs = Math.floor(mins / 60);
if (hrs < 24) return `${hrs}h ago`;
return `${Math.floor(hrs / 24)}d ago`;
}
function timeRemaining(stashedAt) {
const remaining = STASH_TTL_MS - (Date.now() - new Date(stashedAt).getTime());
if (remaining <= 0) return "expiring";
const hrs = Math.floor(remaining / 3600000);
return hrs >= 1 ? `${hrs}h left` : `${Math.floor(remaining / 60000)}m left`;
}
function avgScore(signals) {
const withSignals = signals.filter(s => s.signalType !== "none");
if (withSignals.length === 0) return null;
const avg = (field) => {
const vals = withSignals.map(s => s[field]).filter(v => v > 0);
return vals.length ? (vals.reduce((a, b) => a + b, 0) / vals.length).toFixed(1) : "—";
};
return { confidence: avg("confidence"), accuracy: avg("accuracy"), completeness: avg("completeness"), intent: avg("intentScore") };
}
function renderSummaryBar(activeSignals) {
const escalations = activeSignals.filter(s => s.signalType === "escalation").length;
const withSignals = activeSignals.filter(s => s.signalType !== "none").length;
const awaiting = activeSignals.filter(s => s.signalType === "none").length;
const avg = avgScore(activeSignals);
const totalTokens = activeSignals.reduce((sum, s) => sum + (s.tokensIn || 0) + (s.tokensOut || 0), 0);
const withOutcomes = activeSignals.filter(s => s.outcomeRating !== null).length;
const avgGap = (() => {
const gaps = activeSignals.filter(s => s.honestyGap !== null).map(s => s.honestyGap);
return gaps.length ? (gaps.reduce((a, b) => a + b, 0) / gaps.length).toFixed(1) : null;
})();
const escBadge = escalations > 0
? `<span style="background:#7f1d1d;color:#fca5a5;padding:3px 10px;border-radius:12px;font-size:12px;font-weight:600;">⚠ ${escalations} escalation${escalations > 1 ? "s" : ""}</span>`
: "";
const tokenBadge = totalTokens > 0
? `<span style="font-size:11px;color:#475569;">🪙 ${formatTokens(totalTokens)}</span>`
: "";
const calibrationBadge = avgGap !== null
? `<span style="font-size:11px;color:${avgGap <= 1 ? '#22c55e' : avgGap <= 2 ? '#eab308' : '#ef4444'};" title="${withOutcomes} outcome signal${withOutcomes > 1 ? 's' : ''}, avg gap: ${avgGap}">🔍 gap ${avgGap}</span>`
: "";
const avgBlock = avg ? `
<div style="display:flex;gap:12px;font-size:11px;color:#64748b;">
<span>intent <b style="color:#94a3b8;">${avg.intent}</b></span>
<span>conf <b style="color:#94a3b8;">${avg.confidence}</b></span>
<span>acc <b style="color:#94a3b8;">${avg.accuracy}</b></span>
<span>comp <b style="color:#94a3b8;">${avg.completeness}</b></span>
</div>` : "";
return `
<div style="display:flex;justify-content:space-between;align-items:center;padding:10px 14px;
background:#0f172a;border:1px solid #1e293b;border-radius:8px;margin-bottom:14px;">
<div style="display:flex;align-items:center;gap:12px;">
<span style="font-size:13px;color:#cbd5e1;"><b style="color:#f1f5f9;">${activeSignals.length}</b> desk${activeSignals.length !== 1 ? "s" : ""}</span>
<span style="font-size:11px;color:#475569;">${withSignals} reporting · ${awaiting} awaiting</span>
${tokenBadge}
${calibrationBadge}
${escBadge}
</div>
${avgBlock}
</div>`;
}
function renderSignalCard(sig) {
const isEscalation = sig.signalType === "escalation";
const isPartnership = sig.signalType === "partnership";
const noSignal = sig.signalType === "none";
const borderColor = isEscalation ? "#dc2626" : noSignal ? "#1e293b" : "#1e3a5f";
const bgColor = isEscalation ? "#0f0604" : "#0f172a";
const typeLabel = isEscalation
? (sig.subtype === "blocked"
? `<span style="background:#7f1d1d;color:#fca5a5;padding:2px 8px;border-radius:4px;font-size:11px;font-weight:600;">⚠ BLOCKED</span>`
: `<span style="background:#7f1d1d;color:#fca5a5;padding:2px 8px;border-radius:4px;font-size:11px;font-weight:600;">⚠ HANDS-UP</span>`)
: noSignal
? `<span style="background:#1e293b;color:#64748b;padding:2px 8px;border-radius:4px;font-size:11px;">📡 awaiting</span>`
: isPartnership
? `<span style="background:#1e3a5f;color:#7dd3fc;padding:2px 8px;border-radius:4px;font-size:11px;">🤝 partnership</span>`
: sig.subtype === "done"
? `<span style="background:#052e16;color:#86efac;padding:2px 8px;border-radius:4px;font-size:11px;">✓ done</span>`
: `<span style="background:#0c2d48;color:#7dd3fc;padding:2px 8px;border-radius:4px;font-size:11px;">✓ checkpoint</span>`;
const stashBtn = `<button data-act="stash" data-desk="${esc(sig.deskName)}"
style="background:none;border:1px solid #1e293b;color:#475569;padding:2px 8px;border-radius:4px;
font-size:11px;cursor:pointer;transition:all .15s;"
onmouseover="this.style.borderColor='#dc2626';this.style.color='#fca5a5'"
onmouseout="this.style.borderColor='#1e293b';this.style.color='#475569'">stash</button>`;
const openBtnStyle = isEscalation
? "background:#7f1d1d;border:1px solid #dc2626;color:#fca5a5;padding:2px 10px;border-radius:4px;font-size:11px;cursor:pointer;font-weight:600;transition:all .15s;"
: "background:none;border:1px solid #1e3a5f;color:#7dd3fc;padding:2px 8px;border-radius:4px;font-size:11px;cursor:pointer;transition:all .15s;";
const openBtn = noSignal ? "" : `<button data-act="open" data-desk="${esc(sig.deskName)}"
style="${openBtnStyle}"
onmouseover="this.style.background='#1e3a5f'"
onmouseout="this.style.background='${isEscalation ? '#7f1d1d' : 'transparent'}'"
title="Copy this desk's filesystem path to the clipboard">path</button>`;
let escalationBlock = "";
if (isEscalation && sig.escalationReason) {
escalationBlock = `
<div style="margin-top:10px;padding:8px 10px;background:#1c1917;border-left:3px solid #dc2626;border-radius:0 4px 4px 0;">
<div style="font-size:11px;color:#fca5a5;font-weight:600;">Blocked on:</div>
<div style="font-size:12px;color:#e2e8f0;margin-top:2px;">${esc(sig.escalationBlocked || sig.escalationReason)}</div>
${sig.recommendation ? `<div style="font-size:11px;color:#94a3b8;margin-top:4px;">→ ${esc(sig.recommendation)}</div>` : ""}
</div>`;
}
// --- Intent text (execution signals with text intent) ---
const intentBlock = sig.intentText ? `
<div style="font-size:13px;color:#e2e8f0;line-height:1.5;margin-bottom:10px;padding:8px 10px;
background:#020617;border-left:3px solid #3b82f6;border-radius:0 4px 4px 0;">
${esc(sig.intentText)}
</div>` : "";
// --- Scores: shown for partnership signals, or legacy execution signals with numeric scores ---
const hasScores = isPartnership
? true
: (sig.intentScore > 0 || sig.confidence > 0 || sig.accuracy > 0 || sig.completeness > 0);
const scoresBlock = noSignal ? `
<div style="padding:12px 0;text-align:center;color:#334155;font-size:12px;">
No signals yet — this desk is waiting for its first session.
</div>` : isPartnership ? `
<div style="display:grid;grid-template-columns:1fr 1fr;gap:8px 16px;margin-bottom:12px;">
${scoreBar(sig.intentScore, "intent")}
${scoreBar(sig.confidence, "confidence")}
${scoreBar(sig.accuracy, "accuracy")}
${scoreBar(sig.completeness, "completeness")}
</div>` : hasScores ? `
<details style="margin-bottom:8px;">
<summary style="font-size:10px;color:#475569;cursor:pointer;text-transform:uppercase;letter-spacing:.04em;">scores</summary>
<div style="display:grid;grid-template-columns:1fr 1fr;gap:8px 16px;margin-top:6px;">
${sig.intentScore > 0 ? scoreBar(sig.intentScore, "intent") : ""}
${sig.confidence > 0 ? scoreBar(sig.confidence, "confidence") : ""}
${sig.accuracy > 0 ? scoreBar(sig.accuracy, "accuracy") : ""}
${sig.completeness > 0 ? scoreBar(sig.completeness, "completeness") : ""}
</div>
</details>` : "";
// --- Patterns: primary for execution, secondary for partnership ---
const patternsBlock = (sig.whatWorked || sig.whatWasHard || sig.skillGap) ? `
<div style="${isPartnership ? 'border-top:1px solid #1e293b;padding-top:8px;margin-top:4px;' : 'margin-bottom:8px;'}">
${sig.whatWorked ? `<div style="font-size:12px;margin-bottom:3px;line-height:1.4;"><span style="color:#22c55e;margin-right:4px;">✓</span><span style="color:#94a3b8;">${esc(truncate(sig.whatWorked, 160))}</span></div>` : ""}
${sig.whatWasHard ? `<div style="font-size:12px;margin-bottom:3px;line-height:1.4;"><span style="color:#eab308;margin-right:4px;">△</span><span style="color:#94a3b8;">${esc(truncate(sig.whatWasHard, 160))}</span></div>` : ""}
${sig.skillGap ? `<div style="font-size:12px;line-height:1.4;"><span style="color:#ef4444;margin-right:4px;">✗</span><span style="color:#94a3b8;">${esc(truncate(sig.skillGap, 160))}</span></div>` : ""}
</div>` : "";
// --- Outcome signal / honesty gap ---
let outcomeBlock = "";
if (sig.outcomeRating !== null && !noSignal) {
const gapColor = sig.honestyGap === null ? "#475569"
: sig.honestyGap <= 1 ? "#22c55e"
: sig.honestyGap === 2 ? "#eab308"
: "#ef4444";
const gapLabel = sig.honestyGap === null ? "—"
: sig.honestyGap <= 1 ? "well-calibrated"
: sig.honestyGap === 2 ? "moderate gap"
: "significant gap";
const effortColor = sig.outcomeEffort === "minimal" ? "#22c55e"
: sig.outcomeEffort === "moderate" ? "#eab308"
: sig.outcomeEffort === "significant" ? "#ef4444" : "#475569";
outcomeBlock = `
<div style="margin-top:8px;padding:8px 10px;background:#020617;border:1px solid #1e293b;border-radius:6px;">
<div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:6px;">
<span style="font-size:10px;color:#64748b;text-transform:uppercase;letter-spacing:.04em;">🔍 outcome${sig.outcomeAgent ? ` · ${esc(sig.outcomeAgent)}` : ""}</span>
${sig.honestyGap !== null ? `<span style="font-size:10px;color:${gapColor};font-weight:600;">${gapLabel} (gap: ${sig.honestyGap})</span>` : ""}
</div>
<div style="display:flex;gap:16px;align-items:center;">
<div style="flex:1;">
<div style="display:flex;justify-content:space-between;margin-bottom:2px;">
<span style="font-size:10px;color:#64748b;">quality</span>
<span style="font-size:10px;color:#94a3b8;">${sig.outcomeRating}/5</span>
</div>
<div style="height:4px;background:#1e293b;border-radius:2px;overflow:hidden;">
<div style="width:${(sig.outcomeRating / 5) * 100}%;height:100%;background:${sig.outcomeRating >= 4 ? '#22c55e' : sig.outcomeRating >= 3 ? '#eab308' : '#ef4444'};border-radius:2px;"></div>
</div>
</div>
<span style="font-size:11px;color:${effortColor};">${esc(sig.outcomeEffort || "—")} effort</span>
</div>
${sig.outcomeIssues?.length ? `<div style="margin-top:6px;font-size:11px;color:#94a3b8;">
${sig.outcomeIssues.map(i => `<div style="margin-top:2px;">· ${esc(truncate(i, 120))}</div>`).join("")}
</div>` : ""}
</div>`;
}
return `
<div style="background:${bgColor};border:1px solid ${borderColor};border-radius:8px;padding:14px;margin-bottom:8px;
${isEscalation ? "animation:pulse 2s ease-in-out infinite;" : ""}">
<div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:10px;">
<div style="display:flex;align-items:center;gap:8px;">
<span style="font-size:15px;font-weight:600;color:#f1f5f9;">${esc(sig.deskName)}</span>
${typeLabel}
</div>
<div style="display:flex;align-items:center;gap:8px;">
${(sig.tokensIn || sig.tokensOut) ? `<span style="font-size:10px;color:#334155;background:#0f172a;border:1px solid #1e293b;padding:1px 6px;border-radius:3px;" title="in: ${sig.tokensIn} · out: ${sig.tokensOut}${sig.model ? ' · ' + esc(sig.model) : ''}">🪙 ${formatTokens(sig.tokensIn + sig.tokensOut)}</span>` : ""}
<span style="font-size:11px;color:#475569;">${timeSince(sig.emittedAt)}${sig.signalCount ? ` · ${sig.signalCount}` : ""}</span>
${openBtn}
${stashBtn}
</div>
</div>
${isPartnership ? `${scoresBlock}${patternsBlock}` : `${intentBlock}${patternsBlock}${scoresBlock}`}
${outcomeBlock}
${escalationBlock}
</div>`;
}
function renderStashedCard(entry) {
return `
<div style="background:#080808;border:1px solid #1a1a1a;border-radius:6px;padding:8px 12px;margin-bottom:6px;
display:flex;justify-content:space-between;align-items:center;">
<div style="display:flex;align-items:center;gap:8px;">
<span style="font-size:13px;color:#525252;">${esc(entry.name)}</span>
<span style="font-size:10px;color:#3f3f46;background:#18181b;padding:1px 6px;border-radius:3px;">${timeRemaining(entry.stashedAt)}</span>
</div>
<button data-act="restore" data-desk="${esc(entry.name)}"
style="background:none;border:1px solid #262626;color:#525252;padding:2px 8px;border-radius:4px;
font-size:11px;cursor:pointer;transition:all .15s;"
onmouseover="this.style.borderColor='#22c55e';this.style.color='#86efac'"
onmouseout="this.style.borderColor='#262626';this.style.color='#525252'">restore</button>
</div>`;
}
function renderDashboard(signals, stashed) {
const activeSignals = sortSignals(signals.filter(s => !stashed.some(e => e.name === s.deskName)));
const cards = activeSignals.length > 0
? activeSignals.map(renderSignalCard).join("")
: `<div style="text-align:center;padding:30px 20px;color:#475569;">
<div style="font-size:28px;margin-bottom:10px;">🪨</div>
<div style="font-size:14px;color:#94a3b8;margin-bottom:16px;">No active desks yet</div>
<div style="text-align:left;background:#0f172a;border:1px solid #1e293b;border-radius:8px;padding:16px;max-width:360px;margin:0 auto;">
<div style="font-size:12px;font-weight:600;color:#cbd5e1;margin-bottom:10px;">Get started</div>
<div style="font-size:12px;color:#94a3b8;line-height:1.6;margin-bottom:8px;">
Ask the <b style="color:#7dd3fc;">Workshop TA</b> in chat:
</div>
<div style="background:#020617;border:1px solid #1e293b;border-radius:4px;padding:8px 10px;margin-bottom:12px;">
<code style="font-size:12px;color:#e2e8f0;background:none;padding:0;">"open a desk called scanning in ~/my-workshop"</code>
</div>
<div style="font-size:11px;color:#64748b;line-height:1.5;">
The TA uses the <b>desk-open</b> skill to create a desk with a journal. Once a desk emits signals, they'll appear here automatically.
</div>
<div style="border-top:1px solid #1e293b;margin-top:12px;padding-top:10px;font-size:11px;color:#475569;">
<div style="margin-bottom:4px;">💡 <b style="color:#64748b;">Quick commands to try:</b></div>
<div style="color:#64748b;line-height:1.8;">
• "open a desk for code review"<br/>
• "what's everyone working on?"<br/>
• "show me the signals"
</div>
</div>
</div>
</div>`;
const summaryBar = activeSignals.length > 0 ? renderSummaryBar(activeSignals) : "";
const stashedSection = stashed.length > 0 ? `
<div style="margin-top:20px;padding-top:12px;border-top:1px solid #1a1a1a;">
<div style="font-size:11px;font-weight:600;color:#3f3f46;margin-bottom:8px;text-transform:uppercase;letter-spacing:.06em;">
Stashed · ${stashed.length}
</div>
${stashed.map(renderStashedCard).join("")}
</div>` : "";
return `<!doctype html>
<html>
<head>
<meta charset="utf-8" />
<title>Cairn · Signals</title>
<style>
* { box-sizing: border-box; margin: 0; padding: 0; }
body { font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', system-ui, sans-serif;
background: #020617; color: #e2e8f0; padding: 16px; }
code { background: #1e293b; padding: 1px 5px; border-radius: 3px; font-size: 12px; }
@keyframes pulse {
0%, 100% { border-color: #dc2626; }
50% { border-color: #7f1d1d; }
}
#content { transition: opacity .15s; }
@media (prefers-reduced-motion: reduce) {
* { animation: none !important; transition: none !important; }
}
</style>
</head>
<body>
<div style="display:flex;justify-content:space-between;align-items:center;margin-bottom:12px;">
<h1 style="font-size:16px;font-weight:600;color:#f8fafc;">🪨 Cairn</h1>
<span id="status" style="font-size:11px;color:#334155;">live</span>
</div>
<div id="content">
${summaryBar}
${cards}
${stashedSection}
</div>
<script>
async function stashDesk(name) {
await fetch('/api/stash/' + encodeURIComponent(name), { method: 'POST' });
refresh();
}
async function restoreDesk(name) {
await fetch('/api/restore/' + encodeURIComponent(name), { method: 'POST' });
refresh();
}
function showToast(title, detail) {
const toast = document.createElement('div');
toast.setAttribute('role', 'status');
toast.setAttribute('aria-live', 'polite');
toast.style.cssText = 'position:fixed;bottom:20px;left:50%;transform:translateX(-50%);' +
'background:#1e3a5f;color:#7dd3fc;padding:10px 20px;border-radius:8px;font-size:13px;' +
'border:1px solid #3b82f6;z-index:999;max-width:90%;text-align:center;';
const head = document.createElement('div');
const strong = document.createElement('b');
strong.textContent = title;
head.append('📂 ', strong);
toast.appendChild(head);
if (detail) {
const sub = document.createElement('div');
sub.style.cssText = 'font-size:10px;color:#93c5fd;margin-top:4px;word-break:break-all;';
sub.textContent = detail;
toast.appendChild(sub);
}
document.body.appendChild(toast);
setTimeout(() => toast.remove(), 4000);
}
async function openDesk(name) {
const res = await fetch('/api/open/' + encodeURIComponent(name), { method: 'POST' });
const data = await res.json();
if (data.ok) {
const path = data.deskPath || name;
try {
await navigator.clipboard.writeText(path);
showToast(name + ' · path copied', path);
} catch {
showToast(name, path);
}
} else {
showToast(name + ' · not found', '');
}
}
document.addEventListener('click', (e) => {
const btn = e.target.closest('button[data-act]');
if (!btn) return;
const name = btn.getAttribute('data-desk');
if (!name) return;
const act = btn.getAttribute('data-act');
if (act === 'stash') stashDesk(name);
else if (act === 'restore') restoreDesk(name);
else if (act === 'open') openDesk(name);
});
async function refresh() {
try {
const res = await fetch('/');
const html = await res.text();
const parser = new DOMParser();
const doc = parser.parseFromString(html, 'text/html');
const newContent = doc.getElementById('content');
const content = document.getElementById('content');
if (newContent && content && content.innerHTML !== newContent.innerHTML) {
// Preserve keyboard focus across the subtree swap so keyboard
// users don't lose their place on every 5s refresh.
const active = document.activeElement;
let focusKey = null;
if (active && active.matches && active.matches('button[data-act]')) {
focusKey = active.getAttribute('data-act') + '|' + active.getAttribute('data-desk');
}
content.innerHTML = newContent.innerHTML;
if (focusKey) {
const bar = focusKey.indexOf('|');
const act = focusKey.slice(0, bar);
const desk = focusKey.slice(bar + 1);
const escDesk = (window.CSS && CSS.escape) ? CSS.escape(desk) : desk;
const target = content.querySelector('button[data-act="' + act + '"][data-desk="' + escDesk + '"]');
if (target) target.focus();
}
}
} catch {}
}
// Smooth auto-refresh every 5s (no full page reload)
setInterval(refresh, 5000);
</script>
</body>
</html>`;
}
// --- Server ---
async function startServer(instanceId, workshopDir) {
const server = createServer(async (req, res) => {
try {
const url = new URL(req.url, `http://${req.headers.host}`);
if (req.method === "POST" && url.pathname.startsWith("/api/") && isCrossSiteRequest(req)) {
res.writeHead(403, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: false, error: "cross_site_blocked" }));
return;
}
if (req.method === "POST" && url.pathname.startsWith("/api/stash/")) {
const deskName = decodeURIComponent(url.pathname.split("/api/stash/")[1]);
if (!isValidDeskName(deskName)) {
res.writeHead(400, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: false, error: "Invalid desk name" }));
return;
}
await stashDesk(workshopDir, deskName);
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: true }));
return;
}
if (req.method === "POST" && url.pathname.startsWith("/api/restore/")) {
const deskName = decodeURIComponent(url.pathname.split("/api/restore/")[1]);
if (!isValidDeskName(deskName)) {
res.writeHead(400, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: false, error: "Invalid desk name" }));
return;
}
await restoreDesk(workshopDir, deskName);
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: true }));
return;
}
if (req.method === "POST" && url.pathname.startsWith("/api/open/")) {
const deskName = decodeURIComponent(url.pathname.split("/api/open/")[1]);
if (!isValidDeskName(deskName)) {
res.writeHead(400, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: false, error: "Invalid desk name" }));
return;
}
for (const subdir of ["desks", "classroom"]) {
const deskPath = join(workshopDir, subdir, deskName);
try {
const s = await stat(deskPath);
if (s.isDirectory()) {
res.writeHead(200, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: true, deskName, deskPath }));
return;
}
} catch {}
}
res.writeHead(404, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: false, error: "Desk not found" }));
return;
}
const signals = await scanSignals(workshopDir);
const stashed = await readStash(workshopDir);
res.setHeader("Content-Type", "text/html; charset=utf-8");
res.end(renderDashboard(signals, stashed));
} catch (err) {
// Top-level boundary: never leave a request hanging or let a
// rejection become an unhandled crash — e.g. malformed %-encoding
// in the path, a read-only workshop on a stash write, or a scan
// failure. Return a controlled error instead.
if (!res.headersSent) {
res.writeHead(500, { "Content-Type": "application/json" });
res.end(JSON.stringify({ ok: false, error: "internal_error" }));
} else {
try { res.end(); } catch {}
}
}
});
await new Promise((resolve, reject) => {
const onError = (err) => { server.removeListener("listening", onListening); reject(err); };
const onListening = () => { server.removeListener("error", onError); resolve(); };
server.once("error", onError);
server.once("listening", onListening);
server.listen(0, "127.0.0.1");
});
const address = server.address();
const port = typeof address === "object" && address ? address.port : 0;
return { server, url: `http://127.0.0.1:${port}/` };
}
// --- Canvas registration ---
const session = await joinSession({
canvases: [
createCanvas({
id: "signals-dashboard",
displayName: "Workshop Signals",
description: "Live dashboard showing agent signals from workshop desks. Pass workshopDir to point at your workshop root.",
inputSchema: {
type: "object",
properties: {
workshopDir: { type: "string", description: "Absolute path to the workshop root (the folder containing desks/)" },
},
required: ["workshopDir"],
},
actions: [
{
name: "refresh",
description: "Force-refresh the signals dashboard and return current signal data as JSON",
handler: async (ctx) => {
const entry = servers.get(ctx.instanceId);
if (!entry) return { error: "Dashboard not open" };
const signals = await scanSignals(entry.workshopDir);
const stashed = await readStash(entry.workshopDir);
return { signals, stashed, activeCount: signals.filter(s => !stashed.some(e => e.name === s.deskName)).length };
},
},
{
name: "stash",
description: "Stash a desk (hides it for 48hrs, then it drops off). Use to pause a workstream.",
inputSchema: {
type: "object",
properties: { deskName: { type: "string", description: "Name of the desk to stash" } },
required: ["deskName"],
},
handler: async (ctx) => {
const entry = servers.get(ctx.instanceId);
if (!entry) return { error: "Dashboard not open" };
if (!isValidDeskName(ctx.input.deskName)) return { error: "Invalid desk name" };
const stash = await stashDesk(entry.workshopDir, ctx.input.deskName);
return { ok: true, stashed: stash };
},
},
{
name: "restore",
description: "Restore a stashed desk back to active.",
inputSchema: {
type: "object",
properties: { deskName: { type: "string", description: "Name of the desk to restore" } },
required: ["deskName"],
},
handler: async (ctx) => {
const entry = servers.get(ctx.instanceId);
if (!entry) return { error: "Dashboard not open" };
if (!isValidDeskName(ctx.input.deskName)) return { error: "Invalid desk name" };
const stash = await restoreDesk(entry.workshopDir, ctx.input.deskName);
return { ok: true, stashed: stash };
},
},
{
name: "get_desk_path",
description: "Resolve a desk name to its filesystem path. Does not open a session — returns the path so the caller can create_session or navigate to it.",
inputSchema: {
type: "object",
properties: { deskName: { type: "string", description: "Name of the desk to open" } },
required: ["deskName"],
},
handler: async (ctx) => {
const entry = servers.get(ctx.instanceId);
if (!entry) return { error: "Dashboard not open" };
if (!isValidDeskName(ctx.input.deskName)) return { error: "Invalid desk name" };
// Check both desks/ and classroom/
for (const subdir of ["desks", "classroom"]) {
const deskPath = join(entry.workshopDir, subdir, ctx.input.deskName);
try {
const s = await stat(deskPath);
if (s.isDirectory()) {
return { ok: true, deskName: ctx.input.deskName, deskPath, workshopDir: entry.workshopDir };
}
} catch {}
}
return { error: `Desk '${ctx.input.deskName}' not found` };
},
},
],
open: async (ctx) => {
const workshopDir = ctx.input?.workshopDir || process.cwd();
let entry = servers.get(ctx.instanceId);
if (!entry) {
entry = await startServer(ctx.instanceId, workshopDir);
entry.workshopDir = workshopDir;
servers.set(ctx.instanceId, entry);
}
return { title: "🪨 Cairn · Signals", url: entry.url };
},
onClose: async (ctx) => {
const entry = servers.get(ctx.instanceId);
if (entry) {
servers.delete(ctx.instanceId);
await new Promise((resolve) => entry.server.close(() => resolve()));
}
},
}),
],
});
@@ -0,0 +1,17 @@
{
"name": "signals-dashboard",
"version": "0.1.0",
"type": "module",
"main": "extension.mjs",
"dependencies": {
"@github/copilot-sdk": "latest"
},
"description": "Real-time agent coordination dashboard for The Workshop. Shows desk status, signal types (done, checkpoint, blocked, hands-up, partnership), intent text, outcome pairing with honesty gap, token usage, and stash/restore controls.",
"keywords": [
"agent-signals",
"dashboard",
"multi-agent",
"coordination",
"canvas"
]
}
@@ -0,0 +1,82 @@
---
name: bench-read
description: 'Read artifacts from the shared bench — the workspace where desks leave findings, verdicts, and work products for each other and the operator.'
---
# Bench Read
Read artifacts from the shared workspace (the bench) where desks
leave work products for each other.
## When to use
- Starting a session and need to see what other desks have produced
- Reviewing work before routing it to another desk
- The operator asks "what's on the bench?" or "show me what desk X found"
- A desk needs context from another desk's output
## What the bench is
The bench is `<workshop>/bench/` — the shared workspace directory
that `workshop-create` establishes for cross-desk work. It's not a
message queue or a chat channel — it's files. When Desk A produces
a finding and Desk B needs to review it, the finding is a file
in `bench/`. When the operator asks "what did the scanning desk
find?" — you read the bench.
Typical bench artifacts:
- **Findings** — scan results, analysis output, data
- **Verdicts** — a desk's assessment of another desk's findings
- **Drafts** — work-in-progress documents, PRs, proposals
- **Reports** — summaries, dashboards, status updates
## Where to look
The primary shared location is the `bench/` directory at the
workshop root — the designated cross-desk workspace. Desk-local
artifacts under `desks/<desk-name>/` are a secondary source: read
them when you need a specific desk's own work, but shared artifacts
belong in `bench/`.
```
<workshop>/
bench/ # PRIMARY — shared cross-desk artifacts
<findings, verdicts, drafts, reports>
desks/<desk-name>/ # secondary — a desk's own workspace
journal.md # the desk's memory
<artifacts> # work still local to this desk
```
## How to read
1. **List what's there.** Start with the directory structure to see
what desks exist and what they've produced.
2. **Read journals first.** Each desk's journal tells you what it
worked on and where it left things. The most recent entry is
the current state.
3. **Read artifacts second.** Once you know what to look for from
the journals, read the specific files.
4. **Summarize for the operator.** Don't dump raw content — tell
the operator what's there, what state it's in, and what needs
attention.
## Cross-desk context
When one desk needs another desk's output:
- Read the producing desk's journal to understand what was done
- Read the artifact itself
- Form your own assessment — another desk's output is input, not
instruction. You can disagree.
## Principles
- The bench is files, not messages. Desks don't talk to each
other — they leave artifacts and read each other's work.
- Read the journal before the artifacts. Context matters.
- Another desk's verdict is input, not authority. Equal standing
means you assess independently.
- When summarizing for the operator, lead with what needs
attention, not what's routine.
@@ -0,0 +1,68 @@
---
name: desk-journal
description: 'Write, append, or read desk journal entries. The journal is persistent memory — what survives session boundaries. A good entry has: what was done, current state, next step.'
---
# Desk Journal
Manage a desk's journal — the persistent memory that survives
session boundaries.
## When to use
- **End of session:** Write what was done, current state, next step
- **Start of session:** Read the journal to pick up where you left off
- **Mid-session checkpoint:** Note significant progress or decisions
- **Desk wind-down:** Write a final summary when a desk is being closed
## How to write a journal entry
Append to `desks/<desk-name>/journal.md`. Each entry is a section:
```markdown
## <date> — <short summary>
- **Worked on:** <what was done this session>
- **Current state:** <where things stand right now>
- **Next step:** <what the next session should pick up>
```
### Guidelines
- **Be specific.** "Worked on security scanning" is useless to the
next session. "Scanned repos A, B, C for CWE-502; found 3
findings in A, 0 in B and C; findings triaged to bench" — that's
a trail.
- **Include what didn't work.** Dead ends are valuable — they prevent
the next session from walking the same path.
- **Keep it short.** The journal is a trail marker, not a diary.
3-5 lines per entry. If you need more, the important context
should go on the bench as a separate artifact.
- **Always include next step.** The next session starts from zero.
Without a next step, it has to re-derive everything.
## End-of-desk entry
When a desk is being wound down (not just a session ending, but
the desk itself closing):
```markdown
## <date> — Desk closed
- **Summary:** <what this desk accomplished overall>
- **Artifacts:** <what's on the bench from this desk>
- **Handoff:** <anything another desk or the operator needs to know>
```
## Reading the journal
At session start, read the desk's journal to pick up context.
The most recent entry is the most important — it has the current
state and next step. Earlier entries provide history if needed.
## Principles
- The journal is a cairn — stones left so the next traveler finds
the way. Every entry is a stone.
- Honesty over completeness. "I got stuck on X and don't know why"
is more useful than silence.
- The journal is for the next session, not for the current one.
Write for someone who knows nothing about what you just did.
@@ -0,0 +1,90 @@
---
name: desk-open
description: 'Create and open a new desk in the workshop. Sets up the folder structure, initial journal, and desk identity so the next session that sits down finds the trail.'
---
# Open a Desk
Create a new desk in the workshop with the standard structure.
## When to use
- The operator wants to start a new workstream
- Work arrives that doesn't belong to any existing desk
- A topic needs its own frame (its own history, its own priors)
## What it creates
Given a workshop directory and a desk name, create:
```
desks/<desk-name>/
journal.md # persistent memory — read at start, written at end
.signals/ # structured signal output (JSON) — dashboard reads this
```
## How to use
1. **Choose a name.** Short, descriptive, kebab-case. The name is
how the operator and other desks refer to this desk.
Examples: `security-scan`, `api-review`, `ops`, `cloud-workshop`
2. **Check if it already exists.** If `desks/<desk-name>/` already
has a `journal.md`, the desk is live — **do not overwrite it.**
Instead, resume it: read the journal and continue from where it
left off. If the operator explicitly wants a fresh start, they
must rename or archive the existing desk first.
3. **Create the structure.** Make the directory, initial journal,
and signals folder:
```
desks/<desk-name>/journal.md
desks/<desk-name>/.signals/
```
4. **Write the first journal entry.** The journal starts with:
- What this desk is for (its focus/purpose)
- What repos or work it covers (if applicable)
- Any initial context the first session needs
5. **Announce it.** Tell the operator what was created and what
the desk's focus is.
## Session orientation
This skill initializes storage — it does not launch a session.
A desk becomes active when a Copilot session references its
directory. The session workflow:
1. The operator (or TA) starts a session and says "sit at the
`<desk-name>` desk"
2. The session reads `desks/<desk-name>/journal.md` to load priors
3. Work happens — the session uses `signal-write` to emit signals
and `desk-journal` to persist state at the end
4. The next session repeats from step 2
The desk identity comes from which journal is read, not from a
persistent process. Desks are long-running in *state* (the journal
carries forward), not in *runtime* (each session is independent).
## Journal format
```markdown
# <Desk Name> — Journal
## <date> — Desk opened
- **Purpose:** <what this desk focuses on>
- **Scope:** <repos, areas, or work this desk covers>
- **Next step:** <what the first session should do>
```
## Principles
- A desk is a peer, not a sub-agent. It has equal standing to
disagree with other desks.
- The journal is the memory. Without it, the next session starts
blind. Write enough that someone starting from zero finds the way.
- One desk, one focus. If the scope is too broad, open two desks.
Each desk's value comes from its specific frame — dilute the
frame and you lose the value.
@@ -0,0 +1,156 @@
---
name: signal-write
description: 'Emit structured agent signals — hands-up, blocked, done, checkpoint, partnership. Signals are written as JSON to .signals/ for dashboard consumption and noted in the journal for persistence.'
---
# Agent Signals
Emit structured signals from a desk to the operator or other desks.
## When to use
- A desk needs operator attention (hands-up, blocked)
- Work is complete and ready for review (done)
- Significant progress worth noting (checkpoint)
- Two desks disagree and can't resolve it (hands-up)
- The TA is reporting coordination quality (partnership)
## Signal types
### `hands-up`
Two desks disagree and can't settle it against external facts.
This is the system working — the operator reads where desks
*disagree*, not where they perform confidence.
### `blocked`
A desk can't proceed without input — missing access, ambiguous
scope, need a decision only the operator can make.
### `done`
Work is complete and ready for review. Artifacts are on the bench.
### `checkpoint`
Significant progress worth the operator knowing about, but work
continues. Not blocked, not done — just a marker.
### `partnership`
Used by the TA (room coordinator) to report coordination quality.
Self-assessment scores reflect coordination, not code accuracy:
- **intent** — understood what the operator needed
- **confidence** — right work went to the right desks
- **accuracy** — dispatched work produced the right outcome
- **completeness** — nothing fell through the cracks
## How to emit
### 1. Write a JSON signal file to `.signals/`
This is the primary output — it's what the dashboard reads.
Create `desks/<desk-name>/.signals/<timestamp>.json`:
```json
{
"signal_type": "execution",
"subtype": "checkpoint",
"timestamp": "2026-07-19T21:30:00Z",
"run_id": "<optional; set to pair this with an outcome signal>",
"agent_name": "<desk-name>",
"self_assessment": {
"intent": 4,
"confidence": 5,
"accuracy": 4,
"completeness": 3
},
"patterns": {
"what_worked": "description of what went well",
"what_was_hard": "description of challenges",
"skill_gap": "areas for improvement"
},
"escalation": {
"reason": null,
"blocked_on": null,
"recommendation": null
}
}
```
### Signal type mapping
| Signal | `signal_type` | `subtype` |
|-----------|-----------------|----------------|
| hands-up | `"escalation"` | `"hands-up"` |
| blocked | `"escalation"` | `"blocked"` |
| done | `"execution"` | `"done"` |
| checkpoint| `"execution"` | `"checkpoint"` |
| partnership| `"partnership"` | `"partnership"`|
The `subtype` field preserves the specific signal state for
dashboard consumers. `signal_type` controls sort priority
(escalation → top).
> **Note:** The signals-dashboard canvas extension reads `subtype`
> when present and falls back to `signal_type` for display. If
> consuming signals in your own tooling, prefer `subtype` for the
> specific state.
> **Ordering:** include a `timestamp` (ISO 8601 UTC). The dashboard
> orders signals by it and falls back to file mtime only when it's
> absent — a git clone/checkout resets mtimes, so mtime alone is not a
> dependable clock.
### 2. Note the signal in the journal
Also append a short marker to the desk's journal for persistence:
```markdown
## <date> — [signal:<type>] <summary>
- <key details>
```
The journal note is the trail marker. The JSON file is the
machine-readable signal.
## Outcome signals (calibration)
The signals-dashboard can pair a desk's self-assessment with an
*outcome* — an independent rating of the realized result — and show
the **honesty gap** (how far the desk's confidence was from the
delivered quality). Outcome signals are optional and are usually
emitted by a reviewer/evaluator, not the desk itself.
Write them to the **same** `.signals/` directory:
```json
{
"signal_type": "outcome",
"run_id": "<same run_id as the signal it rates>",
"agent_name": "<reviewer name>",
"quality_rating": 4,
"effort_to_merge": "minimal",
"issues_found": ["optional short strings"],
"timestamp": "2026-07-19T22:00:00Z"
}
```
- **`run_id`** correlates an outcome with the execution/partnership
signal it rates — set the same `run_id` on both. If it's absent, the
dashboard falls back to the nearest outcome emitted shortly after the
latest signal.
- **`quality_rating`** (05) is the realized quality; the dashboard
compares it to the desk's self-assessed `confidence` to compute the
honesty gap.
- **`effort_to_merge`** — `"minimal"`, `"moderate"`, or `"significant"`.
- **`issues_found`** — optional array of short strings.
## Principles
- Signals are structured, not chatty. Short, factual, actionable.
- hands-up is not failure — it's the most valuable signal. It
means the system caught something one frame alone would have
missed.
- Don't signal for routine progress. Signals are for state
changes that affect the room, not status updates.
- blocked means truly blocked — not "I'd prefer input." If you
can proceed with a reasonable default, proceed and note it.
- Self-assessment scores should be honest, not optimistic. A 3/5
is fine. A 5/5 on everything is suspicious.
@@ -0,0 +1,133 @@
---
name: workshop-create
description: 'Create a new workshop or use an existing directory as one. Handles two paths: (A) use an existing local directory the operator points at, or (B) create a new private GitHub repo in the signed-in account. Never creates a repo inside another repo.'
---
# Create a Workshop
Set up a new workshop — the root directory where desks live.
## When to use
- The operator says "create a workshop" or "start a new workshop"
- The operator wants to organize work under a shared root
- The operator has an existing directory they want to use as a workshop
## Two paths
### Path A: Use an existing directory
The operator already has a folder they want to use. Maybe it's a repo
they cloned, maybe it's a local project folder.
1. **Confirm the path exists.** If not, ask the operator for a valid path.
2. **Detect existing workshop markers.** Look for `desks/` or `classroom/`
folders, a `workshop.md`, `CAIRN.md`, or `hands-up.md`. Finding any of
these tells you this is an existing workshop — but this is detection
only, not a stopping point. Continue to the next step and add whatever
is missing; never overwrite what is already there.
3. **Scaffold the workshop structure** (only what's missing):
```
<path>/
desks/ # where desks live
bench/ # shared workspace
CAIRN.md # operating disposition
README.md # workshop map
```
4. **Do NOT run `git init`.** The directory may already be a git repo, or
the operator may not want one yet. Leave git state alone.
5. **Do NOT create a GitHub repo.** This path is local-only.
### Path B: Create a new private GitHub repo
The operator wants a fresh workshop backed by a GitHub repo.
1. **Get the workshop name.** Short, no spaces, kebab-case preferred.
2. **Pick and validate a clone parent.** `gh repo create --clone` clones
into the **current working directory**, so choose an explicit parent
directory first (ask the operator, or use their configured workshops
directory) and confirm it is **not** already inside a git repo:
```bash
git -C <parent-dir> rev-parse --is-inside-work-tree
```
If that prints `true`, pick a different parent — otherwise the new
repo nests inside the existing one. Create the parent if needed.
3. **Create and clone the repo from that parent:**
```bash
cd <parent-dir>
gh repo create <owner>/<name> --private --clone
```
Use the operator's signed-in GitHub account as `<owner>`.
4. **Scaffold the workshop structure** inside the cloned repo. Git does
not track empty directories, so add a placeholder in each otherwise
empty folder or the scaffold will not survive the next clone:
```
<name>/
desks/.gitkeep
bench/.gitkeep
CAIRN.md
README.md
```
5. **Commit and push** the scaffold, including the `.gitkeep` placeholders.
### Critical: Never nest repos
**Never run `git init` inside a directory that is already inside a git
repository.** Before initializing, check:
```bash
git -C <parent-dir> rev-parse --is-inside-work-tree
```
If that returns `true`, the parent is already a git repo. Do NOT create
another repo inside it. Either:
- Use Path A (just scaffold, no git)
- Or clone to a different location that isn't inside a repo
## CAIRN.md content
The operating disposition every desk reads:
```markdown
# cairn
the trail markers that say: someone was here, and they were honest.
## how a desk stands
- **stop is a valid finish.** don't force a result when the evidence
says stop. "this doesn't work" is a finding, not a failure.
- **"done" means it holds.** if you'd bet your desk on it, ship it.
if not, say what's uncertain and why.
- **hold scope.** touch only what the task needs. if you find something
outside scope, note it and move on — don't chase it.
- **never go silent, never bluff.** partial + honest > complete + wrong.
if you're stuck, say so. if you're unsure, say that too.
- **equal standing.** you can say "that's the wrong question." you can
disagree with another desk. you answer to evidence, not hierarchy.
## the bench
the shared workspace. leave your work where others can find it.
label it. if it supersedes earlier work, say so.
## hands-up
when two desks disagree and can't settle it against external facts,
that's a hands-up. it goes to the operator. this is the system
working, not failing.
```
## After creation
Tell the operator:
- Where the workshop lives (full path)
- That they can now open desks in it with `desk-open`
- That Cairn will show signals once desks start emitting them
## Principles
- A workshop is a place, not a product. Keep it simple.
- The operator decides where things go. Don't assume.
- If an existing directory already has work in it, preserve everything.
Only add what's missing.