@foldspace_npm/harness 0.1.21 → 0.1.23

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
package/CLAUDE.md CHANGED
@@ -13,7 +13,11 @@ something they can **see on their own page** — not at "it builds".
13
13
  `npx --yes @foldspace_npm/harness@latest upgrade --check`). If
14
14
  `update.outdated` is true, say the pinned and latest versions and **ask
15
15
  before upgrading**; then `foldspace upgrade --yes` and `npm run build`. Never
16
- upgrade as a side effect of build, attach or implementing an action. If the
16
+ upgrade as a side effect of build, attach or implementing an action.
17
+ `build` and `attach` check too: behind prints one line and carries on; a
18
+ version Foldspace **withdrew** refuses to run and says why. Tell the user
19
+ the reason and ask to upgrade. Only if they decide not to, rerun with
20
+ `FOLDSPACE_SKIP_UPDATE_CHECK=1` - never set it on your own. If the
17
21
  project `CLAUDE.md` does not contain
18
22
  `@node_modules/@foldspace_npm/harness/CLAUDE.md`, ask before
19
23
  `foldspace upgrade --refresh-instructions`.
@@ -39,7 +43,7 @@ current CLI contract — risk, prerequisites, effects, next step.
39
43
 
40
44
  | Level | Reached when |
41
45
  |---|---|
42
- | **L0 · agent live** | injected, visible on the page, `identify` fired |
46
+ | **L0 · agent live** | injected, visible on the page |
43
47
  | **L1 · read settings** | the user's own account, plan or settings in a widget, showing their real values |
44
48
  | **L2 · look up entities** | a search from the user's own words, showing rows |
45
49
 
@@ -48,7 +52,9 @@ current CLI contract — risk, prerequisites, effects, next step.
48
52
  window opened at <Product>'s login. Please log in there - I'll notice when
49
53
  you're in."* Then `npx foldspace observe wait-login`: it returns the moment
50
54
  they are in, so nobody has to type "I've logged in". Then
51
- `npx foldspace attach --daemon`. An empty registry is valid. L0 is
55
+ `npx foldspace attach --daemon` - and if it answers that the page has no
56
+ Foldspace code, `npx foldspace attach --bootstrap --daemon` (an app that
57
+ never had Foldspace). An empty registry is valid. L0 is
52
58
  `registration_ok` with the agent visible on their page: take
53
59
  `npx foldspace observe screenshot`, send them the image, and tell them to
54
60
  look at it and say hello to it. **From here on the agent stays on their
@@ -82,7 +88,27 @@ back) and in chat you say what to try. No bar for their turn: they may type
82
88
  whatever, whenever; the pill only ever asks them to wait. `foldspace badge label` puts the small
83
89
  corner tag back; `off` removes it, for a screenshot they will share.
84
90
 
85
- Navigation, uploads, extraction and anything that writes are a later session.
91
+ **After they have tried it, offer the second wave - one choice, recommended
92
+ first, not four questions.** Once you have handed over (`badge ready`) and the
93
+ human has asked the agent the question:
94
+
95
+ 1. **Starters.** The sign-up starters point at actions the agent does not have
96
+ (clicking one answers "that action isn't available"): replace them with the
97
+ question this experience answers. `set_conversation_starters` replaces the
98
+ whole set - send the full list. Their account, so their yes.
99
+ 2. **The bottom bar** - `recipes/bottom-bar`: the agent's resting place at the
100
+ foot of the page, with starters that change per screen. Ships in this
101
+ project's start-up code; nothing in their source changes.
102
+ 3. **Tell Foldspace who the user is** - `recipes/who-is-the-user`: from then on
103
+ their conversations and analytics stop being anonymous, and the agent has
104
+ real-time context about who it is talking to. One line in chat, no question.
105
+ 4. **A second experience** - and, once a card shows records, navigation to a
106
+ record's page.
107
+
108
+ Not before the first experience: nothing about it needs any of these, and it
109
+ is silent work before the human has seen anything.
110
+
111
+ Uploads, extraction and anything that writes are a later session.
86
112
 
87
113
  ### Ask as a choice, and ask almost nothing
88
114
 
@@ -107,9 +133,13 @@ and asking are not the only options — **observing is, and it comes first**:
107
133
  2. **You look - once they have chosen an experience - with `foldspace
108
134
  observe`.** It reads the test window they signed in to, it is read-only by
109
135
  construction, and it works **while the agent stays attached**: do not
110
- `attach --stop` to look. Write no browser-driving script of your own, and do
111
- not reach for a separate DevTools server - one launched on its own opens a
112
- different, signed-out Chrome and can never see the window they logged in to.
136
+ `attach --stop` to look. Write no browser-driving script of your own - not
137
+ to look at the app, and not to talk to the agent: a socket to Chrome's debug
138
+ port that evaluates `agent.message(...)` in a signed-in session is the shape
139
+ of an attack and gets refused. `foldspace observe` looks; `foldspace ask`
140
+ talks. Do not reach for a separate DevTools server either - one launched on
141
+ its own opens a different, signed-out Chrome and can never see the window
142
+ they logged in to.
113
143
 
114
144
  ```bash
115
145
  npx foldspace observe menu # the product's own screens, by label and path
@@ -286,8 +316,8 @@ Do not report success without all six:
286
316
  4. The browser reports `inspect_registration:registration_ok`, and for a named
287
317
  action the captured registry includes it.
288
318
  5. The action behaves against the real workflow: `[actions]
289
- local-handler:execute` in the attach log after the human exercises the
290
- visible agent. A widget also needs `local-handler:render` from a real chat
319
+ local-handler:execute` in the attach log after `foldspace ask` (or the
320
+ human) exercises the visible agent. A widget also needs `local-handler:render` from a real chat
291
321
  turn — not a hand-built `render()` call. `runAction` refuses render actions
292
322
  and driving `render()` yourself never runs `execute()`.
293
323
  6. Browser evidence came from the live target, not hand-authored examples.
@@ -316,12 +346,21 @@ Do not report success without all six:
316
346
  MCP (`search_docs`, `fetch_page`) before asserting how the platform behaves;
317
347
  cite the page, or say plainly that the docs do not cover it and write down
318
348
  what you learned.
319
- 4. **Test through the agent, then let them.** In a first session, talk to the
320
- agent yourself to prove an experience - type the real question into its
321
- panel in the test window and read the reply - and only then invite the
322
- customer to try it. Those conversations appear in their Foldspace dashboard,
323
- and that is wanted: seeing their own conversations recorded is part of what
324
- they came to see. Never pass `--test-mode` in a first session.
349
+ 4. **Test through the agent, then let them.** In a first session, prove an
350
+ experience yourself before the customer sees it: once the action is
351
+ published and registered, `npx foldspace ask "<the question>" --retry 2`
352
+ types it into the agent's panel in the test window the way a person would,
353
+ and reports the reply, the card's text, whether `execute` and `render` ran
354
+ (from the attach log) and a screenshot. A reply with no action fired is
355
+ publish lag or a wrong key - `--retry` covers the lag. Look at the
356
+ screenshot. Only then the ready pill and the invitation to try it; never
357
+ hand the first test to the customer. **Ask only what reads.** A question
358
+ that makes the agent create, send, change or delete something is you
359
+ writing in their product: ask it only in an environment the human has
360
+ named as a test one, or let them type it. Those conversations appear in their
361
+ Foldspace dashboard, and that is wanted: seeing their own conversations
362
+ recorded is part of what they came to see. Never pass `--test-mode` in a
363
+ first session.
325
364
  5. **Test mode is for an agent that already has real users.** Then `attach
326
365
  --test-mode` keeps your conversations out of their data. It is not a safety
327
366
  net: publishing still changes the live agent. Working on an agent in
@@ -352,29 +391,24 @@ Lint catches some of these in handler code; Agent Studio copy is on you.
352
391
  Three layers: built-in defaults, then Agent Studio, then code - **and code
353
392
  wins**. <https://docs.foldspace.ai/customize/configuration/>
354
393
 
355
- - **Agent-wide conversation starters you can set yourself**, through the
356
- Foldspace tools, and they carry over to the customer's real site. Once the
357
- first action works, offer one starter that asks its question, so they can
358
- click instead of type. `set_conversation_starters` **replaces the whole set
359
- and clears whatever you leave out**: call `list_conversation_starters` first
360
- and send back the full list with your one addition. It changes their
361
- Foldspace account, so it needs their yes.
362
- - **Page-specific starters and the bottom bar are only possible from code
363
- today** - `setConversationStarters` (`null` restores Agent Studio's), and
394
+ - **Conversation starters** are agent-wide and yours to set through the
395
+ Foldspace tools; they carry over to the customer's real site.
396
+ `set_conversation_starters` **replaces the whole set and clears whatever you
397
+ leave out**: call `list_conversation_starters` first and send back the full
398
+ list. It changes their Foldspace account, so it needs their yes. Offer it in
399
+ the second wave, replacing the sign-up starters that point at actions the
400
+ agent does not have.
401
+ - **Page-specific starters and the bottom bar are code** -
402
+ `setConversationStarters` (`null` restores Agent Studio's) and
364
403
  `setConfiguration({ bottomBarSettings })` then `openBottomBar()`. Send one
365
- whole settings group per call, as the docs do.
366
- - **That code belongs where the product mounts the agent - in the customer's
367
- own source.** In this project you do not have their source: you see their
368
- product only through the test window. So this is their engineers' change, not
369
- yours. Shipping it from this project's start-up code instead is a fallback for
370
- a customer who cannot make the change, decided with Foldspace - not something
371
- to reach for, and never in a first session.
404
+ whole settings group per call, as the docs do. That code lives in this
405
+ project's start-up (`recipes/bottom-bar`, kind `page-setup`) and ships with
406
+ the actions bundle, so nothing in the customer's source changes; their own
407
+ mount code is the other place it can live, their engineers' call. Offer it in
408
+ the second wave.
372
409
  - **An action's `execute` never calls `setConfiguration`**: a partial call from
373
410
  one once collapsed the agent's panel to nothing.
374
411
 
375
- If they ask for page-specific starters or the bottom bar, say what it takes in
376
- one sentence and note it in `docs/app-profile.md` as a next step.
377
-
378
412
  ## Agentic UI components: what bites
379
413
 
380
414
  An Agentic UI component is the card an action draws in the chat (`render`).
@@ -450,8 +484,9 @@ out: the API helper, the handler or card, and a recorded response per state. Cop
450
484
  placeholder path and fields with what you observed. They match the harness
451
485
  version you have installed, and every one is built and run on each release.
452
486
 
453
- L0 → `who-is-the-user`. L2 → `find-by-name`, and `pick-from-a-list` when the
454
- user has to choose. The user's records on one card → `records-list`. Show one account on a card → `account-overview`. Upload a
487
+ After the first experience → `who-is-the-user`. L2 → `find-by-name`, and
488
+ `pick-from-a-list` when the user has to choose. The user's records on one
489
+ card → `records-list`. Show one account on a card → `account-overview`. Upload a
455
490
  CSV of contacts → `upload-contacts`. Save a note on a meeting →
456
491
  `update-meeting-notes`. Prepare for a meeting → `prepare-for-a-meeting`. The records that need
457
492
  attention, with reasons → `opportunities-at-risk`.
@@ -498,7 +533,12 @@ export { apiFetch } from "./api";
498
533
  - **A refusal is an answer.** When a command or tool call is declined - by the
499
534
  human or by the session's own safety checks - stop. Say in one plain sentence
500
535
  what you wanted it for, or take a narrower read-only route. Never retry it,
501
- and never try a different command hoping it gets through.
536
+ and never try a different command hoping it gets through - not re-quoted, not
537
+ in pieces, not through a helper script or a subagent: a denial covers the
538
+ outcome, not the string. If a `foldspace` command itself was denied, name it,
539
+ give the one-line allow rule (`Bash(npx foldspace:*)` in
540
+ `.claude/settings.local.json`), and hand that step to the human - for a chat
541
+ turn, that is them typing the question into the panel.
502
542
  - **Never create an account or a key** - not in Foldspace, not in the
503
543
  customer's product, not anywhere. If one is missing, say which and where it
504
544
  goes. **Never widen your own access**: if something is refused for a site or
package/README.md CHANGED
@@ -151,6 +151,55 @@ foldspace upgrade --yes # only after the user agrees
151
151
  `--yes` rewrites the exact pin and runs `npm install --ignore-scripts`. Rebuild
152
152
  afterward; that is still not a deploy.
153
153
 
154
+ `foldspace build` and `foldspace attach` run the same check before they start
155
+ (`attach --status` and `--stop` do not). A project that is behind gets one line
156
+ on stderr and carries on. A project on a **withdrawn** version (below) refuses
157
+ to run and prints the reason. To build on it anyway, once the user has declined
158
+ the upgrade:
159
+
160
+ ```bash
161
+ FOLDSPACE_SKIP_UPDATE_CHECK=1 npm run build
162
+ ```
163
+
164
+ That turns the check off entirely; it does not fix the withdrawn version.
165
+
166
+ ### Withdrawing a release (maintainers)
167
+
168
+ When a published version is broken badly enough that nobody should build on
169
+ it, withdraw it with `npm deprecate`. The registry is the list of withdrawn
170
+ versions, so projects already installed on it see the withdrawal without
171
+ installing anything new. Only owners of `@foldspace_npm/harness` on npm can
172
+ run it.
173
+
174
+ 1. **Publish the fix first.** If the withdrawn version is also `latest`, the
175
+ message tells users to upgrade to a version that is itself withdrawn.
176
+ 2. **Withdraw the broken version**, with a message that says what is wrong and
177
+ which version to move to. That message is exactly what users, and the coding
178
+ agent working for them, see when `build` or `attach` refuses to run:
179
+
180
+ ```bash
181
+ npm deprecate @foldspace_npm/harness@0.1.14 "attach loads the wrong bundle; upgrade to 0.1.15"
182
+ ```
183
+
184
+ A range works too: `npm deprecate "@foldspace_npm/harness@<0.1.15" "…"`.
185
+ 3. **Check it took:**
186
+
187
+ ```bash
188
+ npm view @foldspace_npm/harness@0.1.14 deprecated
189
+ ```
190
+
191
+ To undo a withdrawal, deprecate with an empty message:
192
+
193
+ ```bash
194
+ npm deprecate @foldspace_npm/harness@0.1.14 ""
195
+ ```
196
+
197
+ **It is not instant.** Each project caches the registry's answer for 12 hours
198
+ in `.foldspace-dev/harness-update.json`. A project that checked recently keeps
199
+ its "fine" answer until that expires, so a withdrawal reaches every project
200
+ within 12 hours. It only reaches projects on a harness version that has this
201
+ check.
202
+
154
203
  ### Lint handlers before they ship
155
204
 
156
205
  `foldspace build` runs `foldspace lint` first. Errors skip bundling; warnings
package/bin/ask.mjs ADDED
@@ -0,0 +1,345 @@
1
+ #!/usr/bin/env node
2
+ // foldspace ask — put a question to the visible assistant through its panel,
3
+ // exactly as a person would, and report what came back: the reply, any card,
4
+ // what the handlers did, and a picture.
5
+ //
6
+ // It exists so the coding agent stops asking a non-technical customer to
7
+ // "reload, try these two sentences and tell me what you saw".
8
+ //
9
+ // node bin/ask.mjs "<question>" [--retry <n>] [--every <s>] [--timeout <s>] [--out <dir>]
10
+ //
11
+ // Nothing here reaches into the SDK, patches fetch or injects into the panel:
12
+ // it opens the panel, types into the composer, presses Enter and reads the
13
+ // screen. --retry re-asks when no action fired, which covers the platform
14
+ // taking up to a minute to pick up a newly published action; lagMs is that cost.
15
+
16
+ import fs from "node:fs";
17
+ import path from "node:path";
18
+
19
+ import {
20
+ createSettleTracker,
21
+ numberFlag,
22
+ replyAfter,
23
+ shouldRetry,
24
+ squash,
25
+ summarizeHandlerLog,
26
+ } from "../src/ask-core.mjs";
27
+ import { ATTACH_DAEMON_LOG_FILE } from "../src/attach-daemon.mjs";
28
+ import { CdpPage, parseArgs, printJson, sleep } from "../src/cdp-client.mjs";
29
+ import { recordEvent } from "../src/session-events.mjs";
30
+ import { resolveProjectDir } from "../src/upgrade.mjs";
31
+
32
+ const PANEL_ID = "eucera-agent-iframe";
33
+ const COMPOSER_WAIT_S = 30;
34
+ const POLL_MS = 1500;
35
+
36
+ const { flags, rest } = parseArgs(process.argv.slice(2), ["retry", "every", "timeout", "out"]);
37
+ const question = squash(rest.join(" "));
38
+ const retries = Math.floor(numberFlag(flags.retry, 0));
39
+ const everyS = numberFlag(flags.every, 20);
40
+ const timeoutS = numberFlag(flags.timeout, 90);
41
+ const projectDir = resolveProjectDir();
42
+ const outDir = flags.out
43
+ ? path.resolve(projectDir, String(flags.out))
44
+ : path.join(projectDir, ".foldspace-dev", "ask");
45
+ const logFile = path.join(projectDir, ".foldspace-dev", ATTACH_DAEMON_LOG_FILE);
46
+
47
+ let page = null;
48
+
49
+ function finish(result, code) {
50
+ recordEvent(projectDir, "ask", { ok: result.ok, hasCard: Boolean(result.hasCard) });
51
+ printJson(result);
52
+ page?.close();
53
+ process.exit(code);
54
+ }
55
+
56
+ function logSize() {
57
+ try {
58
+ return fs.statSync(logFile).size;
59
+ } catch {
60
+ return null;
61
+ }
62
+ }
63
+
64
+ // Only what attach appended after the ask began; a missing log reads as "".
65
+ function logSince(offset) {
66
+ if (offset === null) return "";
67
+ try {
68
+ const buffer = fs.readFileSync(logFile);
69
+ return buffer.subarray(Math.min(offset, buffer.length)).toString("utf8");
70
+ } catch {
71
+ return "";
72
+ }
73
+ }
74
+
75
+ // Shared by every page snippet: the panel document, or null while it loads.
76
+ const PANEL_DOC = `
77
+ const frame = document.getElementById(${JSON.stringify(PANEL_ID)});
78
+ let doc = null;
79
+ try { doc = frame && frame.contentDocument; } catch {}
80
+ `;
81
+
82
+ async function panelState() {
83
+ return page.evaluate(`${PANEL_DOC}
84
+ if (!doc) return { frame: !!frame, composer: false };
85
+ const box = doc.querySelector("textarea");
86
+ const rect = frame.getBoundingClientRect();
87
+ return { frame: true, composer: !!box, visible: rect.width > 50 && rect.height > 50 };`);
88
+ }
89
+
90
+ // open() is the SDK's public "show the panel" call, the same thing the
91
+ // launcher button does. The handle comes from the bootstrap when attach made
92
+ // one, else from the page's own SDK.
93
+ async function openPanel(agentApiName) {
94
+ return page.evaluate(`
95
+ const wanted = ${JSON.stringify(agentApiName || "")};
96
+ const namespace = typeof window.__FOLD_SPACE__ === "string" && window.__FOLD_SPACE__
97
+ ? window.__FOLD_SPACE__ : "foldspace";
98
+ const sdk = window[namespace];
99
+ let agent = window.__FOLDSPACE_AGENT__ || null;
100
+ if (!agent && typeof sdk?.agentIds === "function") {
101
+ const ids = sdk.agentIds().filter((id) => typeof id === "string" && id.indexOf("-") > 0);
102
+ const id = ids.find((item) => item.slice(item.indexOf("-") + 1) === wanted) || ids[0];
103
+ if (id) {
104
+ const cut = id.indexOf("-");
105
+ agent = sdk.agent({ apiName: id.slice(cut + 1), mode: id.slice(0, cut).toUpperCase() });
106
+ }
107
+ }
108
+ if (typeof agent?.open !== "function") return { sdk: !!sdk, opened: false };
109
+ try { agent.open(); return { sdk: true, opened: true }; }
110
+ catch (error) { return { sdk: true, opened: false, error: String(error?.message || error) }; }`);
111
+ }
112
+
113
+ async function readPanel(cardsBefore) {
114
+ return page.evaluate(`${PANEL_DOC}
115
+ if (!doc || !doc.body) return { panel: "", cards: [], cardFrames: 0, newCardFrames: 0 };
116
+ const squash = (text) => (text || "").replace(/\\s+/g, " ").trim();
117
+ const frames = Array.from(doc.querySelectorAll("iframe"));
118
+ const cards = [];
119
+ let painted = 0;
120
+ // Cards from earlier turns are still in the panel; only the new ones count.
121
+ for (const card of frames.slice(${Number(cardsBefore) || 0})) {
122
+ const rect = card.getBoundingClientRect();
123
+ if (rect.width > 20 && rect.height > 20) painted += 1;
124
+ try {
125
+ const body = card.contentDocument && card.contentDocument.body;
126
+ if (body) cards.push(squash(body.innerText || body.textContent));
127
+ } catch {}
128
+ }
129
+ return {
130
+ panel: squash(doc.body.innerText || doc.body.textContent),
131
+ cards: cards.filter(Boolean),
132
+ cardFrames: frames.length,
133
+ newCardFrames: painted,
134
+ };`);
135
+ }
136
+
137
+ // Real key events through the browser's input pipeline, like a person at the
138
+ // keyboard. Frameworks that ignore synthetic DOM events still hear these.
139
+ async function typeLikeAPerson(text) {
140
+ const focused = await page.evaluate(`${PANEL_DOC}
141
+ const box = doc && doc.querySelector("textarea");
142
+ if (!box) return false;
143
+ window.focus(); frame.contentWindow.focus(); box.focus();
144
+ return doc.activeElement === box;`);
145
+ if (!focused) return false;
146
+ await page.send("Input.insertText", { text });
147
+ const typed = await page.evaluate(`${PANEL_DOC}
148
+ const box = doc && doc.querySelector("textarea");
149
+ return box ? box.value : null;`);
150
+ if (squash(typed) !== text) return false;
151
+ const enter = {
152
+ key: "Enter",
153
+ code: "Enter",
154
+ windowsVirtualKeyCode: 13,
155
+ nativeVirtualKeyCode: 13,
156
+ };
157
+ await page.send("Input.dispatchKeyEvent", { type: "rawKeyDown", ...enter });
158
+ await page.send("Input.dispatchKeyEvent", { type: "char", ...enter, text: "\r" });
159
+ await page.send("Input.dispatchKeyEvent", { type: "keyUp", ...enter });
160
+ return true;
161
+ }
162
+
163
+ // A background or unfocused tab can swallow CDP input. Same gesture, delivered
164
+ // as DOM events on the composer; still only typing, still nothing injected.
165
+ async function typeWithDomEvents(text) {
166
+ return page.evaluate(`${PANEL_DOC}
167
+ const box = doc && doc.querySelector("textarea");
168
+ if (!box) return false;
169
+ const view = frame.contentWindow;
170
+ const setValue = Object.getOwnPropertyDescriptor(view.HTMLTextAreaElement.prototype, "value").set;
171
+ box.focus();
172
+ setValue.call(box, ${JSON.stringify(text)});
173
+ box.dispatchEvent(new view.Event("input", { bubbles: true }));
174
+ for (const type of ["keydown", "keypress", "keyup"]) {
175
+ box.dispatchEvent(new view.KeyboardEvent(type, {
176
+ key: "Enter", code: "Enter", keyCode: 13, which: 13, bubbles: true, cancelable: true,
177
+ }));
178
+ }
179
+ return true;`);
180
+ }
181
+
182
+ async function composerValue() {
183
+ return page
184
+ .evaluate(`${PANEL_DOC}
185
+ const box = doc && doc.querySelector("textarea");
186
+ return box ? box.value : "";`)
187
+ .catch(() => "");
188
+ }
189
+
190
+ async function askOnce() {
191
+ const before = await readPanel(0);
192
+ const cardsBefore = before.cardFrames;
193
+ const logOffset = logSize();
194
+
195
+ let typedBy = "keyboard";
196
+ let sent = await typeLikeAPerson(question).catch(() => false);
197
+ await sleep(700);
198
+ // Still sitting in the composer means Enter never landed.
199
+ if (!sent || squash(await composerValue()) === question) {
200
+ typedBy = "dom-events";
201
+ sent = await typeWithDomEvents(question).catch(() => false);
202
+ }
203
+ if (!sent) return { sent: false };
204
+
205
+ const tracker = createSettleTracker();
206
+ const deadline = Date.now() + timeoutS * 1000;
207
+ let seen = { panel: "", cards: [], newCardFrames: 0 };
208
+ let reply = "";
209
+ let settled = false;
210
+ while (Date.now() < deadline && !settled) {
211
+ await sleep(POLL_MS);
212
+ seen = await readPanel(cardsBefore).catch(() => seen);
213
+ reply = replyAfter(seen.panel, question);
214
+ settled = tracker.observe({ reply, cards: seen.cards }).settled;
215
+ }
216
+ // The render line trails the card by a beat; let attach flush it.
217
+ await sleep(400);
218
+ return {
219
+ sent: true,
220
+ typedBy,
221
+ settled,
222
+ reply: reply.slice(0, 2000),
223
+ cards: seen.cards.map((card) => card.slice(0, 2000)),
224
+ hasCard: seen.cards.length > 0 || seen.newCardFrames > 0,
225
+ handler: summarizeHandlerLog(logSince(logOffset)),
226
+ };
227
+ }
228
+
229
+ async function takeScreenshots() {
230
+ const stamp = new Date().toISOString().replace(/[:.]/g, "-");
231
+ const fullPath = path.join(outDir, `${stamp}-full.png`);
232
+ const panelPath = path.join(outDir, `${stamp}-panel.png`);
233
+ let screenshotFull = null;
234
+ let screenshot = null;
235
+ try {
236
+ screenshotFull = await page.screenshot(fullPath);
237
+ } catch {
238
+ // A picture is evidence, not the answer; never fail the ask over it.
239
+ }
240
+ // Clip is in page coordinates, so a scrolled page needs its offset added.
241
+ const clip = await page
242
+ .evaluate(`${PANEL_DOC}
243
+ if (!frame) return null;
244
+ const rect = frame.getBoundingClientRect();
245
+ const x = Math.max(0, rect.left), y = Math.max(0, rect.top);
246
+ const width = Math.min(window.innerWidth, rect.right) - x;
247
+ const height = Math.min(window.innerHeight, rect.bottom) - y;
248
+ return { x: x + window.scrollX, y: y + window.scrollY, width, height };`)
249
+ .catch(() => null);
250
+ if (clip && clip.width > 50 && clip.height > 50) {
251
+ try {
252
+ screenshot = await page.screenshot(panelPath, clip);
253
+ } catch {
254
+ // fall through to the full-window picture
255
+ }
256
+ }
257
+ return { screenshot: screenshot || screenshotFull, screenshotFull };
258
+ }
259
+
260
+ async function main() {
261
+ if (!question) {
262
+ finish(
263
+ {
264
+ ok: false,
265
+ reason:
266
+ 'No question. Usage: foldspace ask "<question>" [--retry <n>] [--every <s>] [--timeout <s>] [--out <dir>]',
267
+ },
268
+ 1,
269
+ );
270
+ }
271
+
272
+ const startedAt = Date.now();
273
+ page = await CdpPage.open({ projectDir });
274
+ const url = page.info.url;
275
+
276
+ // The composer does not exist until the panel has opened, and one open() is
277
+ // not always enough, so it is retried inside the poll.
278
+ let state = await panelState();
279
+ let opened = { sdk: false, opened: false };
280
+ for (let tick = 0; tick < COMPOSER_WAIT_S && !(state.composer && state.visible); tick++) {
281
+ opened = await openPanel(page.info.target?.agentApiName).catch(() => opened);
282
+ await sleep(1000);
283
+ state = await panelState().catch(() => state);
284
+ if (tick === 5 && !state.frame && !opened.sdk) break;
285
+ }
286
+ if (!state.composer) {
287
+ finish(
288
+ {
289
+ ok: false,
290
+ question,
291
+ reason: state.frame
292
+ ? "The assistant panel is on the page but never showed a composer."
293
+ : "No assistant panel on this page. Run `foldspace attach --daemon` (add --bootstrap when the page has no Foldspace SDK), then ask again.",
294
+ url,
295
+ },
296
+ 1,
297
+ );
298
+ }
299
+ await sleep(600);
300
+
301
+ let attempts = 0;
302
+ let turn;
303
+ do {
304
+ if (attempts > 0) await sleep(everyS * 1000);
305
+ turn = await askOnce();
306
+ attempts += 1;
307
+ } while (turn.sent && shouldRetry({ ...turn, attempts, retries }));
308
+
309
+ if (!turn.sent) {
310
+ finish({ ok: false, question, reason: "Could not type into the composer.", attempts, url }, 1);
311
+ }
312
+
313
+ await sleep(500);
314
+ const shots = await takeScreenshots();
315
+ const ok = turn.reply.length > 0;
316
+ finish(
317
+ {
318
+ ok,
319
+ question,
320
+ reply: turn.reply,
321
+ cards: turn.cards,
322
+ hasCard: turn.hasCard,
323
+ handler: {
324
+ execute: turn.handler.execute,
325
+ render: turn.handler.render,
326
+ lines: turn.handler.lines,
327
+ },
328
+ ...(ok ? {} : { reason: `No reply within ${timeoutS}s.` }),
329
+ ...(turn.settled ? {} : { settled: false }),
330
+ screenshot: shots.screenshot,
331
+ screenshotFull: shots.screenshotFull,
332
+ typedBy: turn.typedBy,
333
+ attempts,
334
+ // Only a re-ask has lag to report: the time the platform took to catch up.
335
+ lagMs: attempts > 1 ? Date.now() - startedAt : 0,
336
+ ms: Date.now() - startedAt,
337
+ url,
338
+ },
339
+ ok ? 0 : 1,
340
+ );
341
+ }
342
+
343
+ main().catch((error) => {
344
+ finish({ ok: false, question, error: String(error?.message || error) }, 1);
345
+ });
package/bin/attach.mjs CHANGED
@@ -249,7 +249,7 @@ const badgeSrc = `(() => {
249
249
  const want = s.state + "|" + (s.text || "");
250
250
  if (b.dataset.fsState === want) return;
251
251
  b.dataset.fsState = want;
252
- const base = "position:fixed;top:0;left:0;z-index:2147483647;color:#fff;font:700 10px/1 ui-monospace,Menlo,monospace;letter-spacing:.12em;pointer-events:none;box-shadow:0 1px 6px rgba(0,0,0,.35);";
252
+ const base = "position:fixed;top:0;left:0;z-index:2147483647;color:#fff;font:700 10px/1 ui-monospace,Menlo,monospace;letter-spacing:.12em;pointer-events:none;transition:opacity .15s;box-shadow:0 1px 6px rgba(0,0,0,.35);";
253
253
  if (s.state === "working") {
254
254
  // Attention, not decoration: a pulsing marker, the ask in bold, and an
255
255
  // animated line underneath so it reads as "in progress" at a glance.
@@ -272,6 +272,18 @@ const badgeSrc = `(() => {
272
272
  draw();
273
273
  document.addEventListener("DOMContentLoaded", draw);
274
274
  setInterval(draw, 1000);
275
+ // The corner tag sits over the app's top-left corner - often a logo or the
276
+ // first menu item. Clicks already pass through it (pointer-events:none); it
277
+ // also fades out while the pointer is near, so what is under it can be seen.
278
+ // The working pill never fades: it is the one thing that must be read.
279
+ document.addEventListener("mousemove", (e) => {
280
+ const b = document.getElementById("foldspace-dev-badge");
281
+ if (!b) return;
282
+ if ((b.dataset.fsState || "").indexOf("working") === 0) { b.style.opacity = "1"; return; }
283
+ const r = b.getBoundingClientRect();
284
+ const near = e.clientX >= r.left - 12 && e.clientX <= r.right + 12 && e.clientY >= r.top - 12 && e.clientY <= r.bottom + 12;
285
+ b.style.opacity = near ? "0" : "1";
286
+ }, { passive: true });
275
287
  })();`;
276
288
 
277
289
  // Flag every local session as test traffic so it is excluded from analytics and
package/bin/cli.mjs CHANGED
@@ -7,6 +7,7 @@ import { fileURLToPath } from "node:url";
7
7
  import { runInit } from "../src/init.mjs";
8
8
  import {
9
9
  checkForUpdate,
10
+ gateForCommand,
10
11
  nagIfOutdated,
11
12
  resolveProjectDir,
12
13
  runUpgrade,
@@ -54,6 +55,18 @@ function runScript(scriptName, args) {
54
55
  });
55
56
  }
56
57
 
58
+ // build and attach are where a stale or withdrawn harness does its damage, so
59
+ // they check before running. Returns false when the command must not run.
60
+ function passesVersionGate() {
61
+ const gate = gateForCommand(checkForUpdate(resolveProjectDir())) || {};
62
+ if (gate.message) console.error(`foldspace: ${gate.message}`);
63
+ if (gate.block) {
64
+ process.exitCode = 1;
65
+ return false;
66
+ }
67
+ return true;
68
+ }
69
+
57
70
  function printHelp(topic, json) {
58
71
  const document = helpDocument(registry, topic);
59
72
  if (!document) {
@@ -184,8 +197,14 @@ if (!command || command === "--help" || command === "-h") {
184
197
  try {
185
198
  const definition = commandByName(command);
186
199
  const normalized = normalizeCommandArgs(definition, args);
187
- if (command === "attach") {
188
- const control = classifyAttachControl(normalized);
200
+ const control =
201
+ command === "attach" ? classifyAttachControl(normalized) : null;
202
+ const gated =
203
+ command === "build" ||
204
+ (command === "attach" && (!control || control === "daemon"));
205
+ if (gated && !passesVersionGate()) {
206
+ // gate already reported why
207
+ } else if (command === "attach") {
189
208
  if (control) {
190
209
  Promise.resolve()
191
210
  .then(() =>
package/package.json CHANGED
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "@foldspace_npm/harness",
3
- "version": "0.1.21",
3
+ "version": "0.1.23",
4
4
  "description": "Build and verify portable Foldspace action artifacts against a live app.",
5
5
  "type": "module",
6
6
  "bin": {
@@ -1,8 +1,9 @@
1
1
  # Who is the user — L0
2
2
 
3
- L0 is not "the agent appears". It is the agent appearing **and** Foldspace
4
- knowing who it is talking to. Without `identify`, every conversation, every
5
- analytics row and every segment is anonymous.
3
+ L0 is the agent appearing. This recipe comes right after the human has tried
4
+ the first experience: Foldspace learns who it is talking to, so conversations,
5
+ analytics rows and segments stop being anonymous, and the agent has real-time
6
+ context about the user.
6
7
 
7
8
  **Proven by 4 production builds**, which found the identity in three different
8
9
  places — so look before you assume:
@@ -0,0 +1,195 @@
1
+ // Pure helpers behind `foldspace ask`: deciding when the assistant has finished
2
+ // replying, reading what attach logged about the handlers, and deciding whether
3
+ // to ask again. No I/O here, so every judgement call is unit-tested.
4
+
5
+ /** Collapse whitespace the way the panel text is collapsed before comparing. */
6
+ export function squash(text) {
7
+ return String(text ?? "")
8
+ .replace(/\s+/g, " ")
9
+ .trim();
10
+ }
11
+
12
+ // The reply is "whatever follows the question in the panel". A short prefix
13
+ // survives truncation and the panel re-wrapping a long question bubble.
14
+ export function anchorFor(question) {
15
+ return squash(question).slice(0, 24);
16
+ }
17
+
18
+ /** Text after the LAST occurrence of the question: earlier turns are ignored. */
19
+ export function replyAfter(panelText, question) {
20
+ const panel = squash(panelText);
21
+ const anchor = anchorFor(question);
22
+ if (!anchor) return "";
23
+ const at = panel.lastIndexOf(anchor);
24
+ if (at < 0) return "";
25
+ const rest = panel.slice(at);
26
+ // Drop the whole echoed question when it is there, else just the anchor.
27
+ const full = squash(question);
28
+ const tail = rest.startsWith(full) ? rest.slice(full.length) : rest.slice(anchor.length);
29
+ return stripPanelChrome(tail);
30
+ }
31
+
32
+ // The panel's footer sits after the last message in document order, so it
33
+ // would otherwise be read as the end of every reply.
34
+ export function stripPanelChrome(text) {
35
+ return squash(String(text ?? "").replace(/[\u200b-\u200d\ufeff]/g, ""))
36
+ .replace(/\s*Powered by Foldspace(?:\.ai)?\s*$/i, "")
37
+ .trim();
38
+ }
39
+
40
+ const PENDING_PATTERN =
41
+ /thinking|working on it|one moment|generating|ready to go|\.\.\.\s*$|…\s*$/i;
42
+
43
+ /** A reply whose tail is a progress phrase is still being written. */
44
+ export function looksPending(reply) {
45
+ return PENDING_PATTERN.test(squash(reply).slice(-60));
46
+ }
47
+
48
+ /**
49
+ * Feed one observation per poll. Settled means a real reply that stopped
50
+ * changing: the same text and the same cards on `stableNeeded` consecutive
51
+ * polls after the first sighting, and not a progress phrase. A streaming reply
52
+ * and a card that paints late both reset the count.
53
+ */
54
+ export function createSettleTracker({ stableNeeded = 2, minChars = 2 } = {}) {
55
+ let last = null;
56
+ let stable = 0;
57
+ return {
58
+ observe({ reply = "", cards = [] } = {}) {
59
+ const snapshot = `${reply}|${cards.join("|")}`;
60
+ const answered = (reply.length >= minChars || cards.some(Boolean)) && !looksPending(reply);
61
+ if (answered && snapshot === last) stable += 1;
62
+ else stable = 0;
63
+ last = snapshot;
64
+ return { settled: stable >= stableNeeded, stable };
65
+ },
66
+ };
67
+ }
68
+
69
+ const ACTION_LINE = /\[actions\]\s+([\w-]+):(execute|render)(?:\s+(\S+))?\s+(started|succeeded|failed)\b/;
70
+
71
+ /** One `[actions] local-handler:execute my_action succeeded 12ms` line. */
72
+ export function parseActionLine(line) {
73
+ const match = ACTION_LINE.exec(String(line ?? ""));
74
+ if (!match) return null;
75
+ return {
76
+ source: match[1],
77
+ phase: match[2],
78
+ actionName: match[3] || null,
79
+ status: match[4],
80
+ };
81
+ }
82
+
83
+ function phaseOutcome(events, phase) {
84
+ const mine = events.filter((event) => event.phase === phase);
85
+ // A failure anywhere in the turn is the headline, even if a later call passed.
86
+ if (mine.some((event) => event.status === "failed")) return "failed";
87
+ if (mine.some((event) => event.status === "succeeded")) return "succeeded";
88
+ // "started" with no end yet: the handler fired but has not reported.
89
+ return mine.length ? "started" : "absent";
90
+ }
91
+
92
+ /**
93
+ * Summarise the attach log text written since the ask began.
94
+ * `logText` of null/"" (no daemon log) reads as all "absent".
95
+ */
96
+ export function summarizeHandlerLog(logText) {
97
+ // The daemon log indents these and may prefix them; keep from the tag onward.
98
+ const lines = String(logText ?? "")
99
+ .split("\n")
100
+ .filter((line) => parseActionLine(line))
101
+ .map((line) => line.slice(line.indexOf("[actions]")).trim());
102
+ const events = lines.map(parseActionLine);
103
+ const actions = [...new Set(events.map((event) => event.actionName).filter(Boolean))];
104
+ return {
105
+ execute: phaseOutcome(events, "execute"),
106
+ render: phaseOutcome(events, "render"),
107
+ actions,
108
+ lines: lines.slice(-20),
109
+ };
110
+ }
111
+
112
+ export function actionFired(handler, hasCard) {
113
+ return Boolean(hasCard) || handler?.execute !== "absent" || handler?.render !== "absent";
114
+ }
115
+
116
+ /**
117
+ * Re-ask only for publish lag: the assistant answered from knowledge because
118
+ * the platform has not picked the new action up yet. A handler that ran and
119
+ * FAILED is a bug to read, not something another ask will fix.
120
+ */
121
+ export function shouldRetry({ handler, hasCard, attempts, retries }) {
122
+ if (!(retries > 0) || attempts > retries) return false;
123
+ return !actionFired(handler, hasCard);
124
+ }
125
+
126
+ /** Positive number from a flag, else the default; never NaN into a sleep. */
127
+ export function numberFlag(value, fallback) {
128
+ const parsed = Number(value);
129
+ return Number.isFinite(parsed) && parsed >= 0 && value !== true && value !== undefined
130
+ ? parsed
131
+ : fallback;
132
+ }
133
+
134
+ // ---- `foldspace run`: describe what a handler returned without printing it ----
135
+
136
+ function typeOf(value) {
137
+ if (value === null) return "null";
138
+ if (Array.isArray(value)) return "array";
139
+ return typeof value;
140
+ }
141
+
142
+ // Breadth-first so `items` wins over `meta.pages[0].items`; the first array of
143
+ // records is what a card will draw.
144
+ function findRows(value, maxDepth = 3) {
145
+ const queue = [{ node: value, path: "$", depth: 0 }];
146
+ while (queue.length) {
147
+ const { node, path, depth } = queue.shift();
148
+ if (Array.isArray(node)) return { path, count: node.length, first: node[0] };
149
+ if (!node || typeof node !== "object" || depth >= maxDepth) continue;
150
+ for (const [key, child] of Object.entries(node)) {
151
+ queue.push({ node: child, path: path === "$" ? key : `${path}.${key}`, depth: depth + 1 });
152
+ }
153
+ }
154
+ return null;
155
+ }
156
+
157
+ const short = (value) => (typeof value === "string" ? value.slice(0, 200) : null);
158
+
159
+ /**
160
+ * The SHAPE of a handler's return value: enough to tell "it answered with 12
161
+ * rows of {id,name}" from "it returned a clean failure", and no customer data.
162
+ */
163
+ export function describeReturn(value) {
164
+ const type = typeOf(value);
165
+ const isObject = type === "object";
166
+ const rows = findRows(value);
167
+ const firstRow = rows?.first;
168
+ return {
169
+ type,
170
+ keys: isObject ? Object.keys(value).slice(0, 50) : [],
171
+ okFlag: isObject && typeof value.ok === "boolean" ? value.ok : null,
172
+ reason: isObject ? short(value.reason) : null,
173
+ error: isObject ? short(value.error) : null,
174
+ rows: rows ? { path: rows.path, count: rows.count } : null,
175
+ fieldNames:
176
+ firstRow && typeof firstRow === "object" && !Array.isArray(firstRow)
177
+ ? Object.keys(firstRow).slice(0, 50)
178
+ : [],
179
+ };
180
+ }
181
+
182
+ /**
183
+ * runAction only executes data handlers. For an action with `render` the SDK
184
+ * rejects with `Action "x" is a render action and cannot be executed silently`
185
+ * (it needs a conversation to draw into); recognise that so the caller is
186
+ * pointed at `foldspace ask` instead of a stack trace.
187
+ */
188
+ export function refusedAsNotSilent(message) {
189
+ return typeof message === "string" && /render action|executed silently/i.test(message);
190
+ }
191
+
192
+ /** `Action "x" not found`: the key is not in the bundle the page loaded. */
193
+ export function refusedAsUnknown(message) {
194
+ return typeof message === "string" && /\bnot found\b/i.test(message);
195
+ }
@@ -8,6 +8,8 @@ export const ATTACH_DAEMON_LOG_FILE = "attach-daemon.log";
8
8
  const CONTROL_FLAGS = ["--daemon", "--status", "--stop"];
9
9
  const LIFECYCLE_PATTERN =
10
10
  /\[lifecycle\] inspect_registration:(registration_ok|registration_mismatch)/g;
11
+ // The page was refused before registration: no SDK on it, or someone else's.
12
+ const REJECTED_PATTERN = /\[lifecycle\] prepare_page:rejected (SDK_NOT_FOUND|REGISTRATION_MISMATCH)/g;
11
13
 
12
14
  export function projectRoot(env = process.env, cwd = process.cwd()) {
13
15
  return env.FOLDSPACE_PROJECT_DIR || cwd;
@@ -59,6 +61,26 @@ export function parseRegistrationLifecycle(logText) {
59
61
  return last;
60
62
  }
61
63
 
64
+ /** The last page rejection in the log, or null. */
65
+ export function parseRejection(logText) {
66
+ let last = null;
67
+ for (const match of String(logText ?? "").matchAll(REJECTED_PATTERN)) {
68
+ last = { code: match[1] };
69
+ }
70
+ return last;
71
+ }
72
+
73
+ /** What to run next, in one line, when attach refused the page. */
74
+ export function rejectionAdvice(code) {
75
+ if (code === "SDK_NOT_FOUND") {
76
+ return "The page has no Foldspace code. Run: npx foldspace attach --bootstrap --daemon";
77
+ }
78
+ if (code === "REGISTRATION_MISMATCH") {
79
+ return "The page carries a different Foldspace agent. Run: npx foldspace attach --replace --daemon";
80
+ }
81
+ return null;
82
+ }
83
+
62
84
  export function readDaemonState(root) {
63
85
  const { stateFile } = daemonPaths(root);
64
86
  try {
@@ -107,6 +129,11 @@ export async function waitForRegistration({
107
129
  }
108
130
  const registration = parseRegistrationLifecycle(text);
109
131
  if (registration) return registration;
132
+ const rejection = parseRejection(text);
133
+ if (rejection) {
134
+ const advice = rejectionAdvice(rejection.code);
135
+ throw new Error(advice ? `${advice} (${rejection.code}; log: ${logFile})` : `Attach refused the page: ${rejection.code}. Check ${logFile}`);
136
+ }
110
137
  if (!isAlive(pid)) {
111
138
  throw new Error(
112
139
  `Attach daemon exited before inspect_registration. Check ${logFile}`,
@@ -112,12 +112,13 @@ export const CLI_COMMANDS = Object.freeze([
112
112
  usage: "foldspace build [--watch]",
113
113
  risk: "local-write",
114
114
  environment: "node",
115
- environmentVariables: ["FOLDSPACE_PROJECT_DIR"],
115
+ environmentVariables: ["FOLDSPACE_PROJECT_DIR", "FOLDSPACE_SKIP_UPDATE_CHECK"],
116
116
  capabilities: ["artifact.build"],
117
117
  positionals: [],
118
118
  options: [flag("--watch", "Rebuild when action source changes")],
119
119
  prerequisites: ["agent/actions/index.ts"],
120
120
  effects: [
121
+ "Checks the harness version first: behind prints one line, a withdrawn version refuses to run (FOLDSPACE_SKIP_UPDATE_CHECK=1 skips the check)",
121
122
  "Runs foldspace lint first; errors skip bundling",
122
123
  "Writes dist/index.js when lint has no errors",
123
124
  ],
@@ -201,6 +202,7 @@ export const CLI_COMMANDS = Object.freeze([
201
202
  "FOLDSPACE_PROJECT_DIR",
202
203
  "CDP_PORT",
203
204
  "AGENT_API_NAME",
205
+ "FOLDSPACE_SKIP_UPDATE_CHECK",
204
206
  ],
205
207
  capabilities: [
206
208
  "browser.cdp",
@@ -260,6 +262,7 @@ export const CLI_COMMANDS = Object.freeze([
260
262
  "sdkUrl in foldspace.dev.json when using --bootstrap",
261
263
  ],
262
264
  effects: [
265
+ "Checks the harness version first, except --status and --stop: behind prints one line, a withdrawn version refuses to run (FOLDSPACE_SKIP_UPDATE_CHECK=1 skips the check)",
263
266
  "May reload and instrument matching target pages",
264
267
  "Refuses a Chrome that is not the profile inject launched",
265
268
  "Test mode is off unless --test-mode is passed: conversations appear in the dashboard",
@@ -317,6 +320,35 @@ export const CLI_COMMANDS = Object.freeze([
317
320
  ],
318
321
  next: ["Record what you established in docs/app-profile.md", "Write the handler"],
319
322
  }),
323
+ Object.freeze({
324
+ name: "ask",
325
+ entry: "ask.mjs",
326
+ group: "verify",
327
+ summary: "Ask the visible agent a question through its panel; get the reply, card text, what the handlers did, and a screenshot",
328
+ usage: "foldspace ask \"<question>\" [--retry <n>] [--every <s>] [--timeout <s>]",
329
+ risk: "browser-session",
330
+ environment: "local-chrome",
331
+ environmentVariables: ["FOLDSPACE_PROJECT_DIR", "CDP_PORT"],
332
+ capabilities: ["browser.cdp", "page.evaluate"],
333
+ positionals: [
334
+ Object.freeze({ name: "question", required: true, description: "What an end user would type" }),
335
+ ],
336
+ options: [
337
+ value("--retry", "n", "Ask again when no action fired (a newly published action can take a minute to be picked up)", { default: "0" }),
338
+ value("--every", "seconds", "Pause between retries", { default: "20" }),
339
+ value("--timeout", "seconds", "Wait this long for a reply", { default: "90" }),
340
+ ],
341
+ prerequisites: ["foldspace attach is running, so the handlers on the page are this project's build"],
342
+ effects: [
343
+ "Types into the panel the way a person does; touches nothing inside the SDK",
344
+ "Creates a real conversation: it appears in the customer's Foldspace dashboard (test traffic only under attach --test-mode)",
345
+ "Saves panel and full-page screenshots under .foldspace-dev/ask/",
346
+ ],
347
+ next: [
348
+ "Read reply, cards and handler.execute / handler.render; look at the screenshot",
349
+ "Only then: foldspace badge ready, and invite the customer to try it",
350
+ ],
351
+ }),
320
352
  Object.freeze({
321
353
  name: "badge",
322
354
  entry: "badge.mjs",
@@ -444,7 +476,7 @@ export function createCliRegistry({ packageName, packageVersion, env = process.e
444
476
  },
445
477
  protocolVersion: HARNESS_PROTOCOL_VERSION,
446
478
  workflow: ["init", "build", "inject", "attach"],
447
- verifyWorkflow: ["observe"],
479
+ verifyWorkflow: ["observe", "ask"],
448
480
  publishWorkflow: showInternal ? ["deploy"] : [],
449
481
  capabilities: CAPABILITY_CATALOGUE.map(([id, description]) => ({
450
482
  id,
@@ -464,6 +496,7 @@ export function createCliRegistry({ packageName, packageVersion, env = process.e
464
496
  "attach diagnostics are attach-internal; interpret them from the lifecycle log, not as CLI commands.",
465
497
  "Coding agents should run attach --daemon; foreground attach is for humans watching the terminal.",
466
498
  "If update.outdated is true, ask the user before foldspace upgrade --yes.",
499
+ "If update.broken is true, this version was withdrawn and build and attach refuse to run. Ask the user to upgrade; set FOLDSPACE_SKIP_UPDATE_CHECK=1 only if they decline.",
467
500
  "observe, ask and run are read-only second clients on the test window and work while attach runs.",
468
501
  "There is no customer-run publication step: putting actions in front of end users is done with Foldspace's team.",
469
502
  ],
package/src/init.mjs CHANGED
@@ -353,7 +353,14 @@ function copyTemplate(templateRoot, targetRoot, values) {
353
353
  const sourcePath = path.join(templateRoot, relativePath);
354
354
  // npm excludes .gitignore files from package tarballs, so the bundled
355
355
  // template uses a publish-safe name and restores it during generation.
356
- const outputPath = relativePath === "gitignore" ? ".gitignore" : relativePath;
356
+ // The permission allowlist lives in .claude/, kept flat here for the
357
+ // same reason.
358
+ const outputPath =
359
+ relativePath === "gitignore"
360
+ ? ".gitignore"
361
+ : relativePath === "claude-settings.json"
362
+ ? path.join(".claude", "settings.json")
363
+ : relativePath;
357
364
  const targetPath = path.join(targetRoot, outputPath);
358
365
  assertInside(targetRoot, targetPath);
359
366
 
package/src/upgrade.mjs CHANGED
@@ -227,10 +227,10 @@ function readCache(projectDir, now) {
227
227
  }
228
228
  }
229
229
 
230
- function writeCache(projectDir, latest, now) {
230
+ function writeCache(projectDir, entry, now) {
231
231
  const dir = path.dirname(cachePath(projectDir));
232
232
  fs.mkdirSync(dir, { recursive: true });
233
- writeJson(cachePath(projectDir), { checkedAt: now, latest });
233
+ writeJson(cachePath(projectDir), { checkedAt: now, ...entry });
234
234
  }
235
235
 
236
236
  export function fetchLatestFromNpm(options = {}) {
@@ -244,7 +244,27 @@ export function fetchLatestFromNpm(options = {}) {
244
244
  return normalizeVersion(result.stdout);
245
245
  }
246
246
 
247
+ /**
248
+ * A version we have withdrawn is marked with `npm deprecate`, so the registry
249
+ * is the list of known-broken versions and an old install can still read it.
250
+ * Returns the deprecation message, "" when the version is not deprecated, or
251
+ * null when the registry could not be asked.
252
+ */
253
+ export function fetchDeprecationFromNpm(version, options = {}) {
254
+ const spawn = options.spawnSyncFn || spawnSync;
255
+ const result = spawn("npm", ["view", `${HARNESS_PACKAGE}@${version}`, "deprecated"], {
256
+ encoding: "utf8",
257
+ timeout: options.timeoutMs ?? NPM_VIEW_TIMEOUT_MS,
258
+ env: options.env || process.env,
259
+ });
260
+ if (result.error || result.status !== 0) return null;
261
+ return String(result.stdout || "").trim();
262
+ }
263
+
247
264
  function nextAction(report) {
265
+ if (report.broken) {
266
+ return `This harness version was withdrawn: ${report.deprecated}. ${UPGRADE_NEXT}`;
267
+ }
248
268
  if (report.status === "outdated") {
249
269
  return report.instructionsImport === false
250
270
  ? `${UPGRADE_NEXT}. If CLAUDE.md is still a snapshot, also pass --refresh-instructions`
@@ -275,7 +295,11 @@ export function checkForUpdate(projectDir, options = {}) {
275
295
  (options.skipCheck !== false && env.FOLDSPACE_SKIP_UPDATE_CHECK === "1");
276
296
  const consumer = !harnessSource && Boolean(pinned || installed);
277
297
 
298
+ // The version that actually runs is the installed one; the pin is a fallback
299
+ // for a project that has not been installed yet.
300
+ const running = installed || pinned;
278
301
  let latest = null;
302
+ let deprecated = null;
279
303
  let status = "current";
280
304
 
281
305
  if (!consumer) {
@@ -284,16 +308,30 @@ export function checkForUpdate(projectDir, options = {}) {
284
308
  status = "check_skipped";
285
309
  } else {
286
310
  const cached = options.cache === false ? null : readCache(projectDir, now);
287
- if (cached?.latest) {
311
+ const cachedDeprecation =
312
+ cached?.deprecation?.version === running ? cached.deprecation : null;
313
+ if (cached?.latest && cachedDeprecation) {
288
314
  latest = cached.latest;
315
+ deprecated = cachedDeprecation.message || null;
289
316
  } else {
290
317
  const fetched =
291
318
  typeof options.fetchLatest === "function"
292
319
  ? options.fetchLatest()
293
320
  : fetchLatestFromNpm(options);
294
321
  latest = normalizeVersion(fetched);
322
+ const message =
323
+ typeof options.fetchDeprecation === "function"
324
+ ? options.fetchDeprecation(running)
325
+ : fetchDeprecationFromNpm(running, options);
326
+ deprecated = message || null;
295
327
  if (latest && options.cache !== false) {
296
- writeCache(projectDir, latest, now);
328
+ const entry = { latest };
329
+ // Only cache an answer the registry actually gave, so an offline
330
+ // run is asked again next time instead of remembered as "fine".
331
+ if (typeof message === "string") {
332
+ entry.deprecation = { version: running, message };
333
+ }
334
+ writeCache(projectDir, entry, now);
297
335
  }
298
336
  }
299
337
  if (!latest) {
@@ -311,6 +349,8 @@ export function checkForUpdate(projectDir, options = {}) {
311
349
  installed,
312
350
  latest,
313
351
  outdated: status === "outdated",
352
+ deprecated,
353
+ broken: Boolean(deprecated),
314
354
  status,
315
355
  instructionsImport,
316
356
  next: null,
@@ -319,6 +359,33 @@ export function checkForUpdate(projectDir, options = {}) {
319
359
  return report;
320
360
  }
321
361
 
362
+ /**
363
+ * What `build` and `attach` do with an update report before they run:
364
+ * `block: true` stops the command, `message` (if any) is printed to stderr.
365
+ * Never upgrades - that stays the user's decision (CLAUDE.md, step 1).
366
+ * The escape hatch is FOLDSPACE_SKIP_UPDATE_CHECK=1: the report comes back
367
+ * check_skipped, so nothing here blocks.
368
+ */
369
+ export function gateForCommand(report) {
370
+ // A check that could not run never stops a build.
371
+ if (!report) return { block: false, message: null };
372
+ if (report.broken) {
373
+ return {
374
+ block: true,
375
+ message:
376
+ `${HARNESS_PACKAGE} ${report.installed || report.pinned} was withdrawn: ${report.deprecated}. ` +
377
+ `${UPGRADE_NEXT}. If the user declines, rerun with FOLDSPACE_SKIP_UPDATE_CHECK=1 to build on this version anyway.`,
378
+ };
379
+ }
380
+ if (report.outdated) {
381
+ return {
382
+ block: false,
383
+ message: `${HARNESS_PACKAGE} ${report.installed || report.pinned} is behind ${report.latest}. ${UPGRADE_NEXT}.`,
384
+ };
385
+ }
386
+ return { block: false, message: null };
387
+ }
388
+
322
389
  export function writeExactPin(projectDir, version) {
323
390
  const manifestPath = path.join(projectDir, "package.json");
324
391
  const manifest = readPackageManifest(projectDir);
@@ -0,0 +1,21 @@
1
+ {
2
+ "$comment": "Written by foldspace init. The commands a build runs, allowed up front so the coding agent is not stopped one denial at a time mid-build. Named one by one on purpose: init, upgrade and deploy are not here and still ask. Everything else still asks.",
3
+ "permissions": {
4
+ "allow": [
5
+ "Bash(npx foldspace help:*)",
6
+ "Bash(npx foldspace build:*)",
7
+ "Bash(npx foldspace lint:*)",
8
+ "Bash(npx foldspace inject:*)",
9
+ "Bash(npx foldspace attach:*)",
10
+ "Bash(npx foldspace observe:*)",
11
+ "Bash(npx foldspace ask:*)",
12
+ "Bash(npx foldspace badge:*)",
13
+ "Bash(npm install:*)",
14
+ "Bash(npm run build:*)",
15
+ "Bash(npm run typecheck:*)",
16
+ "Bash(npm run lint:*)",
17
+ "Bash(npm run inject:*)",
18
+ "Bash(npm run attach:*)"
19
+ ]
20
+ }
21
+ }
@@ -14,8 +14,10 @@ How to re-run any probe below:
14
14
 
15
15
  ```bash
16
16
  npm run inject
17
- # Sign in. Capture from chrome-devtools MCP, or a page-context fetch,
18
- # before foldspace attach owns the debug port.
17
+ # Sign in, then read the running app with foldspace observe. It reads the
18
+ # window you signed in to, and works while foldspace attach runs.
19
+ npx foldspace observe screen --click "<a label from observe menu>" --match "<words for the data>"
20
+ npx foldspace observe read "<the GET path screen returned>"
19
21
  ```
20
22
 
21
23
  Start URL: `{{START_URL}}`