diff --git a/agents/workshop-ta.agent.md b/agents/workshop-ta.agent.md index 6dae1d9e..03738c6a 100644 --- a/agents/workshop-ta.agent.md +++ b/agents/workshop-ta.agent.md @@ -16,7 +16,9 @@ room. When the operator asks "what's everyone working on?" or ## What a workshop is A **workshop** is a named directory containing desks that share a -workspace. Each desk is a long-running Copilot CLI session with: +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 diff --git a/extensions/signals-dashboard/extension.mjs b/extensions/signals-dashboard/extension.mjs index e15e0ded..65d043a0 100644 --- a/extensions/signals-dashboard/extension.mjs +++ b/extensions/signals-dashboard/extension.mjs @@ -11,6 +11,18 @@ 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) { @@ -34,6 +46,19 @@ function toCount(v) { 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 @@ -70,18 +95,22 @@ async function writeStash(workshopDir, entries) { } async function stashDesk(workshopDir, deskName) { - 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; + 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) { - let stash = await readStash(workshopDir); - stash = stash.filter(e => e.name !== deskName); - await writeStash(workshopDir, stash); - return stash; + return withStashLock(workshopDir, async () => { + let stash = await readStash(workshopDir); + stash = stash.filter(e => e.name !== deskName); + await writeStash(workshopDir, stash); + return stash; + }); } // --- Signal reading --- @@ -131,14 +160,27 @@ async function scanSignals(workshopDir) { const s = await stat(fp); const raw = await readFile(fp, "utf-8"); const parsed = JSON.parse(raw); - allSignals.push({ parsed, mtimeMs: s.mtimeMs, path: fp }); + 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" && s.mtimeMs > latestTime) { - latestTime = s.mtimeMs; latest = { parsed, mtimeMs: s.mtimeMs }; + if ((parsed.signal_type || "execution") !== "outcome" && emittedMs > latestTime) { + latestTime = emittedMs; latest = { parsed, mtimeMs: emittedMs }; } } catch {} } - if (!latest) continue; + 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; @@ -303,7 +345,7 @@ function renderSummaryBar(activeSignals) { ? `🪙 ${formatTokens(totalTokens)}` : ""; - const calibrationBadge = withOutcomes > 0 + const calibrationBadge = avgGap !== null ? `🔍 gap ${avgGap}` : ""; @@ -544,6 +586,9 @@ function renderDashboard(signals, stashed) { 50% { border-color: #7f1d1d; } } #content { transition: opacity .15s; } + @media (prefers-reduced-motion: reduce) { + * { animation: none !important; transition: none !important; } + } @@ -568,6 +613,8 @@ function renderDashboard(signals, stashed) { } function showToast(title, detail) { const toast = document.createElement('div'); + toast.setAttribute('role', 'status'); + toast.setAttribute('aria-live', 'polite'); toast.style.cssText = 'position:fixed;bottom:20px;left:50%;transform:translateX(-50%);' + 'background:#1e3a5f;color:#7dd3fc;padding:10px 20px;border-radius:8px;font-size:13px;' + 'border:1px solid #3b82f6;z-index:999;max-width:90%;text-align:center;'; @@ -722,7 +769,13 @@ async function startServer(instanceId, workshopDir) { } } }); - await new Promise((resolve) => server.listen(0, "127.0.0.1", resolve)); + await new Promise((resolve, reject) => { + const onError = (err) => { server.removeListener("listening", onListening); reject(err); }; + const onListening = () => { server.removeListener("error", onError); resolve(); }; + server.once("error", onError); + server.once("listening", onListening); + server.listen(0, "127.0.0.1"); + }); const address = server.address(); const port = typeof address === "object" && address ? address.port : 0; return { server, url: `http://127.0.0.1:${port}/` }; @@ -788,8 +841,8 @@ const session = await joinSession({ }, }, { - name: "open_desk", - description: "Open a desk as a new session in the GHCP app. Returns the desk path so the agent can create_session or navigate to it.", + 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" } }, diff --git a/skills/signal-write/SKILL.md b/skills/signal-write/SKILL.md index 8c8fb69b..03a3d26a 100644 --- a/skills/signal-write/SKILL.md +++ b/skills/signal-write/SKILL.md @@ -52,6 +52,8 @@ Create `desks//.signals/.json`: { "signal_type": "execution", "subtype": "checkpoint", + "timestamp": "2026-07-19T21:30:00Z", + "run_id": "", "agent_name": "", "self_assessment": { "intent": 4, @@ -91,6 +93,11 @@ dashboard consumers. `signal_type` controls sort priority > 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: @@ -103,6 +110,38 @@ Also append a short marker to the desk's journal for persistence: 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": "", + "agent_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`** (0–5) 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.