mosaicstack/stack
25
0 Fork 1
Code Issues 404 Pull Requests 13 Packages Projects Releases 15 Wiki Activity

test: assert creative history in its native session store

Browse Source 
Apply only the paths and legacy absence pins approved by mos-1420 and sage-3243. Preserve exact expected history and the stopped run evidence. No product change or rerun.
This commit is contained in:
Rocko authored and Jason Woltje committed 2026-10-23 02:11:06 -05:00
1 parent 30cf103017
commit 28bf34f272
27 files changed
+1689 -142
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

agents/rocko/work/queue-219/BUILD.md
+24
View File
@@ -260,3 +260,27 @@ legacy store assertions stay unchanged. Only the specified comment changes.
No product bytes change. If inference is wrong, report red, no third edit.
Dewey must inspect this test diff before the next full restart. Local commit
only while294 holds; push waits for Sage's named gap. No runs after this edit.
## Third edit and new manifest round r2: mos-1420 / sage-3243
Full restart on7cbd839d0 began06:09:43.706Z and stopped06:10:30.695Z:
creative4/0/0, threads19/0/0, user-principal23/0/0, launcher34/0/0,
thread-launch13/1/0, total93 pass/1 fail/0 skip. Persona's exact two-row pin
passed. The new creative-history test failed ENOENT on its obsolete legacy
history path, after its real send/reply checks. Always-running Bean refusal
passed; sandbox-dependent Bean assertion followed the failed read and was
not reached. No coverage claim for that assertion. Slot returned after empty
cwd sweep and14 hashes checked. Original earlier red output was archived
byte-identically before this restart; all later stages unrun.
Mos-1420 authorizes exactly the two history-path corrections in that new
test: obtain each default session from the real runtime threadsState and
read the literal threads/acme/T/sessions/<session>/session/history path.
Contents remain exactly Bean input\nBean again\n and Chet input\n.
Add one literal legacy-path nonexistence assertion per thread, no mkdir
helper. Every other file line stays unchanged. No product change.
The new r2/ manifest/patch snapshot is this third-edit round; root manifest
is refreshed to the same digest for the next claimant/review handoff.
Local commit only; Dewey checks mos1420 items1-3 before push/restart, and
Sage names a gap/CLEAR after294 round4. No runs after this edit. Any further
red, including later lines in this test, returns to Mos through Sage.
agents/rocko/work/queue-219/archive-before-mos1418.sha256
+9
View File
@@ -0,0 +1,9 @@
4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945 agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/cwd-sweep-final.json
4f53cda18c2baa0c0354bb5f9a3ecbe5ed12ab4d8e11ba873c2f11161202b945 agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/cwd-sweep.json
4c7009747c39843d6666ca54bb56d0f2bf991ab81bb514fa6d45053b8f6e4b92 agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/head.json
e86cfe9d1e28b8b42e9ed47c1a5836e4f9f09e700dc892935d55092785ece429 agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/network-cleanup.log
4fd1875a14b5da6e55effa090416b39529e5e00eb54660c2574727624d97ec4d agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/results.jsonl
4898d4ece63c8dcad3346c0a661087531b8b9c5471b6c49a023c4eede65726cb agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-bus-creative.test.tap
0d7e7b8a83c2d6441fe76403615839b26c0863b09e536ee77bcdafa62dd43948 agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-bus-threads.test.tap
1d4bc4439cfd51773a66efd88d22fe1d6bb826c7511a2b1b92e5040ebc293448 agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-bus-user-principal.test.tap
ededb8288ffdb04001aa39bc77d29f7f7ea9ff6cf57f814ea2bd743b4f9fbc8d agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-cli-launcher.test.tap
agents/rocko/work/queue-219/build.patch
+6 -4
View File
@@ -314,7 +314,7 @@ index 2202c7753..baabd843e 100644
test("row 64 on Claude Code a role skill that isn't enabled refuses the same way, before anything starts", { timeout: 30000 }, async (t) => {
diff --git a/packages/cli/tests/thread-launch.test.mjs b/packages/cli/tests/thread-launch.test.mjs
index 0d207a0a0..84f8ed088 100644
index 0d207a0a0..fa3adb866 100644
--- a/packages/cli/tests/thread-launch.test.mjs
+++ b/packages/cli/tests/thread-launch.test.mjs
@@ -396,6 +396,22 @@ test("REQ-THREAD-1 REQ-LAUNCH-1 the chief can't launch the assistant outside a t
@@ -340,7 +340,7 @@ index 0d207a0a0..84f8ed088 100644
// Row 125 (#1619, REQ-LIMIT-3, REQ-LIMIT-4): the token-limit check switched on, with the
// assistant's limit at 0, so it is at its limit before any turn. The real check runs through the
// bus's plug-in loader.
@@ -443,3 +459,71 @@ test("REQ-LIMIT-4 a thread run at its token limit stops at the end of its turn:
@@ -443,3 +459,73 @@ test("REQ-LIMIT-4 a thread run at its token limit stops at the end of its turn:
assert.deepEqual(threadRuns(f, A), []);
assert.equal(host.runtime.threadsState("acme").find((x) => x.thread === A).holder, null);
});
@@ -371,8 +371,10 @@ index 0d207a0a0..84f8ed088 100644
+ assert.deepEqual((await send(bean, 'bean', 'Bean input')).before, []);
+ assert.deepEqual((await send(chet, 'chet', 'Chet input')).before, []);
+ assert.deepEqual((await send(bean, 'bean', 'Bean again')).before, ['Bean input']);
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', bean, 'session', 'history'), 'utf8'), 'Bean input\nBean again\n');
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', chet, 'session', 'history'), 'utf8'), 'Chet input\n');
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', bean, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === bean).session, 'session', 'history'), 'utf8'), 'Bean input\nBean again\n');
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', chet, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === chet).session, 'session', 'history'), 'utf8'), 'Chet input\n');
+ assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', bean, 'session')), false);
+ assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', chet, 'session')), false);
+ const launches = launchLog(f).filter(row => row.event === 'launch');
+ assert.ok(launches.some(row => row.instance === 'bean' && row.thread === bean));
+ assert.ok(launches.some(row => row.instance === 'chet' && row.thread === chet));
agents/rocko/work/queue-219/candidate-manifest.sha256
+1 -1
View File
@@ -4,7 +4,7 @@ de4913f50801a11fd172e3f2c2b3cb41ab04e84d32a6650d1c8662b5e227ea3d packages/bus/t
8f7d6745fffb2a0898ac80c012084ac48964748da6439a8c56facc6529ffb19b packages/bus/tests/user-principal.test.mjs
b74275ce43249bafc97edc87a6a3aa0431c62fe1a28cd9fa265246e6d6da219b packages/cli/src/launcher.mjs
2c3f120dfdc0b52bf8ab38a88e86251be75d4b0d218e23df489dcaf815d6bc15 packages/cli/tests/launcher.test.mjs
a219036737419870e0aa9d0da20843759a66be5bafff44d3292593833f8fcb9a packages/cli/tests/thread-launch.test.mjs
7f308fdf601e839194f026beb3fea279eba1e356ce2756aa4a42fa4873b79b30 packages/cli/tests/thread-launch.test.mjs
cbfd54e6b375561d1e4679ee8d78a3285f970d9a7198cec9d22a06510a36afba packages/webui/src/chat-http.mjs
f49a49c6ec69783190d3f5eaf34316cb4d2c44d10d2ee9336fe1383207afefff packages/webui/src/chat.mjs
8e89df5fe8a9da35de41b5968afc6efcd92503e92ef28c6f557bb5371d10d1a4 packages/webui/src/public/chat.js
agents/rocko/work/queue-219/r2/BUILD.md
+6
View File
@@ -0,0 +1,6 @@
# Row219 r2 / mos1420 third edit
See ../BUILD.md for the full unchanged scope and preserved red chronology.
This round changes only the new thread-launch native-history paths and adds
the two legacy-path absence assertions approved by mos1420. No run yet.
Dewey pre-restart diff check and Sage push/run CLEAR are required.
agents/rocko/work/queue-219/r2/base.txt
+1
View File
@@ -0,0 +1 @@
4a9c536e861f1d9f9a018019b3ac4519d65eccf0
agents/rocko/work/queue-219/r2/build.patch
+788
View File
@@ -0,0 +1,788 @@
diff --git a/packages/bus/src/broker.mjs b/packages/bus/src/broker.mjs
index d76085739..11061c778 100644
--- a/packages/bus/src/broker.mjs
+++ b/packages/bus/src/broker.mjs
@@ -4,7 +4,7 @@ import { initializeControl, processingStatus } from '../../processing-control/sr
import { NAME as HARNESS_NAME } from '../../plugins/src/kinds.mjs';
import { loadRequirements } from '../../tasks/src/requirements.mjs';
import { MERGE, LandingRefusal, readLanding } from './landing.mjs';
-import { ID_PATTERN, THREAD_DEFINITION, END_PROTECTED, forkProblem, forkUrl, credentialKind, validArgv, commandAllowed, HOST_ID, CREATIVE_DEFINITIONS, unhireableAction, giteaName, parseGiteaUrl, covers } from '../../business/src/vocabulary.mjs';
+import { ID_PATTERN, THREAD_DEFINITIONS, END_PROTECTED, forkProblem, forkUrl, credentialKind, validArgv, commandAllowed, HOST_ID, CREATIVE_DEFINITIONS, unhireableAction, giteaName, parseGiteaUrl, covers } from '../../business/src/vocabulary.mjs';
// Kept closed while S1 lands; its vocabulary is the integration authority.
export const ACTIONS = Object.freeze([
@@ -314,7 +314,7 @@ const enrollBinding = (enroll) => ({
});
// r6 E3: the installer line's comment, then the tag's 32 hex digits.
const INSTALLER_COMMENT = 'mosaic-installer-';
-// Row 121 (#1615): an instance of THREAD_DEFINITION (vocabulary.mjs since row 155) talks with the
+// Row 121 (#1615): an instance of THREAD_DEFINITIONS (vocabulary.mjs since row 213) talks with the
// user in threads. Its runs claim a thread, not the role, and every message to or from it names its
// thread (REQ-MSG-1).
// Row 146 (#1640): the sender of the bus's notice to launch.by. A role instance name matches the
@@ -598,7 +598,7 @@ export class Broker {
);
}
#threaded(business, role) {
- return this.#business(business).roles[role]?.definition === THREAD_DEFINITION;
+ return THREAD_DEFINITIONS.includes(this.#business(business).roles[role]?.definition);
}
// Row 264a (#1769): a claim holds one session of a thread, and each session has its own holder.
#sessionHolder(session) {
@@ -6068,24 +6068,27 @@ export class Broker {
.all('SELECT id,at,name,repo FROM projects WHERE business=? ORDER BY seq', s.business)
.filter((p) => !s.user || this.#granted(s, 'project.list', p.id, null));
}
- // A thread belongs to the user who made it and to the business's one thread instance.
+ // A thread belongs to the user who made it and to one declared thread instance.
// Row 177 (#1675): a tester's thread is owned by `tester`, so neither reaches the other's.
case 'thread.create': {
if (!s.tester && !s.user) this.#human(s);
- keys(a, ['project', 'name'], ['project', 'name']);
+ keys(a, ['project', 'name', 'instance'], ['project', 'name']);
if (!name(a.name)) fail('invalid-request');
+ const instances = Object.keys(b.roles).filter((r) => this.#threaded(s.business, r));
+ const instance = a.instance === undefined
+ ? (instances.length === 1 ? instances[0] : null)
+ : identifier(a.instance);
// FED R3 (design 3.5): a user's grant must cover the project and the thread instance, checked
// before the project is looked up, so an ungranted id reads the same whether it exists or not.
if (s.user) {
- const threaded = Object.keys(b.roles).filter((r) => this.#threaded(s.business, r));
- if (threaded.length !== 1 || !this.#granted(s, 'thread.create', identifier(a.project), threaded[0])) fail('access-refused');
+ if (!instance || !instances.includes(instance) || !this.#granted(s, 'thread.create', identifier(a.project), instance))
+ fail('access-refused');
}
if (!this.#store.get('SELECT 1 FROM projects WHERE id=? AND business=?', identifier(a.project), s.business))
fail('project-not-found');
- // The bus never picks between instances; the business file declares exactly one.
- const instances = Object.keys(b.roles).filter((r) => this.#threaded(s.business, r));
- if (!instances.length) fail('thread-instance-missing');
- if (instances.length > 1) fail('thread-instance-ambiguous');
+ // The human selects an instance; omission is compatible only with one candidate.
+ if (!instances.length || (a.instance !== undefined && !instances.includes(instance))) fail('thread-instance-missing');
+ if (a.instance === undefined && instances.length > 1) fail('thread-instance-ambiguous');
if (this.#store.get('SELECT 1 FROM threads WHERE project=? AND name=?', a.project, a.name)) fail('thread-exists');
const tid = randomUUID();
this.#store.run(
@@ -6094,13 +6097,13 @@ export class Broker {
this.#now(),
s.business,
a.project,
- instances[0],
+ instance,
this.#owner(s),
a.name,
);
// Row 264a (#1769, D3): every thread has a default session from the start.
- this.#newSession(s, { id: tid, business: s.business, instance: instances[0], owner: this.#owner(s) }, 'default', 'default', true);
- return { id: tid, instance: instances[0] };
+ this.#newSession(s, { id: tid, business: s.business, instance, owner: this.#owner(s) }, 'default', 'default', true);
+ return { id: tid, instance };
}
// Row 177 (#1675): each lists its own threads. The human's list leaves out the tester's,
// and the tester's lists only its own (row 175 listed it the business human's).
diff --git a/packages/bus/tests/creative.test.mjs b/packages/bus/tests/creative.test.mjs
index 6cfbf1cd6..6d421ba19 100644
--- a/packages/bus/tests/creative.test.mjs
+++ b/packages/bus/tests/creative.test.mjs
@@ -44,15 +44,18 @@ function setup(t) {
const caps = {};
caps.human = b.bindHuman({ business: 'demo', human: 'jason', via: 'cli', outsideAgent: true });
const project = b.request(caps.human, { verb: 'project.create', args: { name: 'demo' } }).id;
- const thread = b.request(caps.human, { verb: 'thread.create', args: { project, name: 'main' } }).id;
+ const thread = b.request(caps.human, { verb: 'thread.create', args: { project, name: 'main', instance: 'assistant' } }).id;
+ const threads = { assistant: thread };
for (const role of Object.keys(roles)) {
- caps[role] = b.bindLaunch({ business: 'demo', role, run: `${role}-run`, harness: 'pi', ...(role === 'assistant' ? { thread } : {}) });
+ if (['bean', 'quill'].includes(role))
+ threads[role] = b.request(caps.human, { verb: 'thread.create', args: { project, name: role, instance: role } }).id;
+ caps[role] = b.bindLaunch({ business: 'demo', role, run: `${role}-run`, harness: 'pi', ...(threads[role] ? { thread: threads[role] } : {}) });
b.request(caps[role], { verb: 'role.claim' });
}
caps.tester = b.bindTester({ business: 'demo' });
const call = (who, verb, args = {}) => b.request(caps[who], { verb, args });
const count = (sql) => store.get(sql).n;
- return { call, count, store };
+ return { call, count, store, threads };
}
const raise = { action: 'policy.change', question: 'Change?', options: [{ key: 'yes', text: 'Yes' }, { key: 'no', text: 'No' }], recommendation: 'yes', blocking: false };
@@ -72,7 +75,7 @@ test('M6: a creative raise refuses decision-not-allowed, cited or not, and no de
});
test('a creative instance sends only to the user and hears only from the user', (t) => {
- const { call, count } = setup(t);
+ const { call, count, threads } = setup(t);
for (const who of ['bean', 'quill']) {
call(who, 'message.send', { to: 'human', body: 'hello' });
for (const to of ['chief', 'assistant', 'pm', 'bean', 'quill'].filter((n) => n !== who)) {
@@ -81,7 +84,7 @@ test('a creative instance sends only to the user and hears only from the user',
for (const from of ['chief', 'pm']) {
assert.throws(() => call(from, 'message.send', { to: who, body: 'hello' }), { code: 'message-sender-refused' }, `${from} to ${who}`);
}
- call('human', 'message.send', { to: who, body: 'hello' });
+ call('human', 'thread.send', { thread: threads[who], body: 'hello' });
}
assert.equal(count("SELECT count(*) n FROM messages WHERE from_role IN ('bean','quill')"), 2);
assert.equal(count("SELECT count(*) n FROM messages WHERE to_role IN ('bean','quill')"), 2);
diff --git a/packages/bus/tests/threads.test.mjs b/packages/bus/tests/threads.test.mjs
index 8b31da9f9..1410ec3fa 100644
--- a/packages/bus/tests/threads.test.mjs
+++ b/packages/bus/tests/threads.test.mjs
@@ -601,3 +601,42 @@ test('project.create keeps unrelated names with and without a repository', t =>
{ id: linked.id, name: 'work', repo: 'stack' },
]);
});
+
+test('C2-09a: explicit creative instances bind independent threads, default sessions and holders', t => {
+ const creative = ['companion', 'ideas', 'research', 'proofreader', 'fact-checker', 'continuity'];
+ const extra = Object.fromEntries(creative.map((definition, i) => [`writer${i}`, { definition, authority: { withinRole: ['message.send'], crossRole: [] } }]));
+ const ctx = setup(t, demo({ roles: { ...roles, ...extra }, definitions: {
+ ...definitions, ...Object.fromEntries(creative.map(definition => [definition, { messaging: shipped(definition).messaging }])),
+ } }));
+ const project = ctx.call('human', 'project.create', { name: 'Writing' }).id;
+ assert.throws(() => ctx.call('human', 'thread.create', { project, name: 'ambiguous' }), { code: 'thread-instance-ambiguous' });
+ for (const [instance, role] of Object.entries(extra)) {
+ const receipt = ctx.call('human', 'thread.create', { project, name: instance, instance });
+ assert.equal(receipt.instance, instance);
+ assert.equal(ctx.store.get('SELECT instance FROM threads WHERE id=?', receipt.id).instance, instance);
+ assert.equal(ctx.store.get('SELECT instance FROM sessions WHERE thread=?', receipt.id).instance, instance);
+ ctx.launch(instance, instance, { thread: receipt.id });
+ assert.equal(ctx.claim(instance).thread, receipt.id);
+ const sent = ctx.call('human', 'thread.send', { thread: receipt.id, body: `For ${instance}` });
+ const read = ctx.call(instance, 'message.receive');
+ assert.deepEqual(read.map(m => m.id), [sent.id], role.definition);
+ assert.equal(ctx.threadOf(sent.id), receipt.id);
+ assert.equal(ctx.store.get('SELECT count(*) n FROM role_claims WHERE role=?', instance).n, 0);
+ assert.throws(() => ctx.call('human', 'message.send', { to: instance, body: 'No implicit thread' }),
+ { code: 'thread-required-use-thread-send' });
+ }
+ assert.equal(ctx.count('SELECT count(*) n FROM threads'), creative.length);
+});
+
+test('C2-09a: explicit missing, non-thread and malformed selectors create no thread or session', t => {
+ const ctx = setup(t);
+ const project = ctx.call('human', 'project.create', { name: 'Writing' }).id;
+ for (const instance of ['not-declared', 'pm', 'coder'])
+ assert.throws(() => ctx.call('human', 'thread.create', { project, name: instance, instance }), { code: 'thread-instance-missing' });
+ for (const instance of [null, 7, {}, [], '', 'bad name'])
+ assert.throws(() => ctx.call('human', 'thread.create', { project, name: 'bad', instance }), { code: 'invalid-request' });
+ assert.equal(ctx.count('SELECT count(*) n FROM threads'), 0);
+ assert.equal(ctx.count('SELECT count(*) n FROM sessions'), 0);
+ const legacy = ctx.call('human', 'thread.create', { project, name: 'Default' });
+ assert.equal(legacy.instance, 'assistant');
+});
diff --git a/packages/bus/tests/user-principal.test.mjs b/packages/bus/tests/user-principal.test.mjs
index 4dcd1ebeb..8471ddf85 100644
--- a/packages/bus/tests/user-principal.test.mjs
+++ b/packages/bus/tests/user-principal.test.mjs
@@ -23,7 +23,7 @@ const grant = (over = {}) => ({
});
// `processing` stands in for the halt switch, as lifecycle-verbs.test.mjs's T15 does.
-function setup(t, { grants = [grant()], processing = null } = {}) {
+function setup(t, { grants = [grant()], processing = null, threadRoles = {} } = {}) {
const root = mkdtempSync(join(tmpdir(), 'bus-user-principal-'));
const store = new Store(root);
t.after(() => {
@@ -40,6 +40,7 @@ function setup(t, { grants = [grant()], processing = null } = {}) {
roles: {
chief: { definition: 'chief-of-staff', authority: { withinRole: ['message.send'], crossRole: [] } },
assistant: { definition: 'assistant', authority: { withinRole: ['message.send'], crossRole: [] } },
+ ...threadRoles,
},
definitions: { 'chief-of-staff': {}, assistant: { messaging: shipped('assistant').messaging } },
},
@@ -394,3 +395,21 @@ test('R3 r4: the chief\'s hire refuses an instance named user with the code it g
test('R3 r4: a non-function access throws before the store is read', () => {
assert.throws(() => new Broker({ store: null, businesses: { demo: {} }, access: 'access.json' }), /access must be a function/);
});
+
+test('C2-09a: naming an instance cannot bypass its collaborator grant or disclose an ungranted project', t => {
+ const ctx = setup(t, { threadRoles: { bean: { definition: 'companion', authority: { withinRole: ['message.send'], crossRole: [] } } } });
+ const project = ctx.call('human', 'project.create', { name: 'shared' }).id;
+ const privateProject = ctx.call('human', 'project.create', { name: 'private' }).id;
+ ctx.access.doc.grants = [grant({ projects: [project] })];
+ ctx.user('alice');
+ assert.equal(ctx.code('alice', 'thread.create', { project, name: 'blocked bean', instance: 'bean' }), 'access-refused');
+ for (const id of [privateProject, '00000000-0000-4000-8000-000000000000'])
+ assert.equal(ctx.code('alice', 'thread.create', { project: id, name: 'blocked project', instance: 'assistant' }), 'access-refused');
+ assert.equal(ctx.store.get('SELECT count(*) n FROM threads').n, 0);
+ const allowed = ctx.call('alice', 'thread.create', { project, name: 'assistant work', instance: 'assistant' });
+ assert.equal(allowed.instance, 'assistant');
+ ctx.access.doc.grants = [grant({ projects: [project], instances: ['bean'] })];
+ const bean = ctx.call('alice', 'thread.create', { project, name: 'bean work', instance: 'bean' });
+ assert.equal(bean.instance, 'bean');
+ assert.equal(ctx.code('alice', 'thread.create', { project, name: 'old instance', instance: 'assistant' }), 'access-refused');
+});
diff --git a/packages/cli/src/launcher.mjs b/packages/cli/src/launcher.mjs
index bfe55b61e..d8248284c 100644
--- a/packages/cli/src/launcher.mjs
+++ b/packages/cli/src/launcher.mjs
@@ -53,7 +53,7 @@
// session.json names it as gitSocket.
//
// Thread sessions (row 121, #1615). A thread instance (an instance whose
-// role definition is the assistant) runs once per thread, never on its own:
+// role definition is in THREAD_DEFINITIONS) runs once per thread, never on its own:
// a launch from a session or --pm refuses thread-required. Every tick
// (threadTickMs) the host asks the broker for the business's threads
// (launch op threadsState) and:
@@ -139,6 +139,7 @@ import { createServer } from "node:net";
import { chmodSync, existsSync, lstatSync, mkdirSync, readFileSync, renameSync, rmSync } from "node:fs";
import { dirname, join, relative } from "node:path";
import { configDir, loadBusiness, resolveInstance, systemVars } from "../../business/src/index.mjs";
+import { THREAD_DEFINITIONS } from "../../business/src/vocabulary.mjs";
import { limitHit } from "../../business/src/launch.mjs";
import { BundleError, buildBundle, hasFallback, readSkills, sessionModel } from "../../harness/src/bundle.mjs";
import { createLoader } from "../../plugins/src/loader.mjs";
@@ -176,8 +177,6 @@ const STOP_TIMEOUT_MS = 30000;
const LINE_MAX = 4096;
// How often the host asks for the threads' state; a poll period, not a limit.
const THREAD_TICK_MS = 2000;
-// The broker's thread instance definition (packages/bus/src/broker.mjs).
-const THREAD_DEFINITION = "assistant";
// Row 194: the broker's LIFECYCLE_REQUEST_MS. A regenerate's old run must be gone by then.
const LIFECYCLE_REQUEST_MS = 60000;
@@ -331,7 +330,7 @@ export function createLauncher({
try { b=loadBusiness(host.business,{dir:configDir(env),rolesDir:rolesDir(env)}); } catch(e){throw new Refusal("organization-refused",e.message);}
if (!b.launch) throw new Refusal("launch-not-configured", `business ${b.id} has no launch block`);
if (!(pm ? instance === b.launch.by : b.launch.instances.includes(instance) || (human && Object.hasOwn(b.roles, instance)))) throw new Refusal("instance-not-listed");
- const threaded = b.roles[instance]?.definition === THREAD_DEFINITION;
+ const threaded = THREAD_DEFINITIONS.includes(b.roles[instance]?.definition);
if (threaded && !thread) throw new Refusal("thread-required", `${instance} runs only for a thread`);
if (!threaded && thread) throw new Refusal("thread-not-allowed", `${instance} isn't a thread instance`);
if (threaded && !session) throw new Refusal("session-required", `${instance} runs for one session of a thread`);
@@ -997,7 +996,7 @@ export function createLauncher({
function ending(r) {
const runs = r.runs ?? [];
const at = Date.parse(r.at);
- const threaded = b.roles[r.instance]?.definition === THREAD_DEFINITION;
+ const threaded = THREAD_DEFINITIONS.includes(b.roles[r.instance]?.definition);
return registry.sessions.filter((s) => s.business === b.id && (runs.includes(s.run) ||
(!threaded && s.instance === r.instance && (spawnedAt.get(s.run) ?? Date.parse(s.startedAt)) <= at)));
}
diff --git a/packages/cli/tests/launcher.test.mjs b/packages/cli/tests/launcher.test.mjs
index 2202c7753..baabd843e 100644
--- a/packages/cli/tests/launcher.test.mjs
+++ b/packages/cli/tests/launcher.test.mjs
@@ -773,21 +773,34 @@ test("row 213 a creative instance's persona is read from <configDir>/personas: o
const dir = join(given.root, "config", "personas", "acme");
mkdirSync(dir, { recursive: true, mode: 0o700 });
writeFileSync(join(dir, "bean.md"), "Not the pinned text.\n", { mode: 0o600 });
- const { f, host, launcher } = await setup(t, undefined, given);
- // The chief of staff holds role.launch; a test chief session bound to this process asks.
- const chief = await host.bindLaunch({ business: "acme", role: "chief", run: "chief-test", harness: "pi", pid: process.pid, startTime: startTimeOf(process.pid) });
- await new Client({ path: host.path, cap: chief.cap }).call("role.claim");
- // The bundle's refusal comes back as launch-failed, as webPlan's does, with its reason in the log.
- assert.deepEqual(await launcher.fromSession(chief.cap, "bean"), { ok: false, error: "launch-failed" });
- const [e] = log(f);
- assert.deepEqual([e.event, e.code, log(f).length], ["refused", "launch-failed", 1]);
+ // Row 219: creative instances launch from their thread, not from a chief's standalone request.
+ // The mismatch occurs before bindLaunch, so only the host's thread-state snapshot is a fixture.
+ const thread = 'persona-thread';
+ const SESSION = 'persona-session';
+ const { f, launcher } = await setup(t, undefined, given, { wrap: host => ({
+ ...host,
+ op: message => message.op === 'threadsState'
+ ? Promise.resolve([{ thread, session: SESSION, instance: 'bean', holder: null, pending: 1 }])
+ : host.op(message),
+ }) });
+ // The thread path records row 270's run-start count before the bundle's persona refusal.
+ await launcher.tick();
+ const runs = readdirSync(join(f.dataRoot, "launches", "acme"));
+ const entries = log(f);
+ assert.equal(entries.length, 2);
+ const { at, ...compactions } = entries[0];
+ assert.deepEqual(compactions, { event: 'compactions', instance: 'bean', thread, session: SESSION, run: runs[0], count: 0, known: true, reason: null });
+ const e = entries[1];
+ assert.deepEqual([e.event, e.code], ["refused", "launch-failed"]);
+ assert.equal(e.thread, thread);
assert.equal(e.why, `instance bean: persona file ${join(dir, "bean.md")} isn't the file persona.sha256 names`);
assert.ok(!JSON.stringify(log(f)).includes("PERSONA-MARKER-d2"));
assert.deepEqual(readSessions(f.dataRoot), []);
// The run directory exists by then (BUILD.md residual); the persona is read before any bundle file.
- const runs = readdirSync(join(f.dataRoot, "launches", "acme"));
assert.equal(runs.length, 1);
- assert.deepEqual(readdirSync(join(f.dataRoot, "launches", "acme", runs[0])), ["session"]);
+ assert.deepEqual(readdirSync(join(f.dataRoot, "launches", "acme", runs[0])), []);
+ assert.equal(existsSync(join(f.dataRoot, "threads", "acme", thread, "sessions", SESSION, "session")), true);
+ assert.equal(existsSync(join(f.dataRoot, "threads", "acme", thread, "session")), false);
});
test("row 64 on Claude Code a role skill that isn't enabled refuses the same way, before anything starts", { timeout: 30000 }, async (t) => {
diff --git a/packages/cli/tests/thread-launch.test.mjs b/packages/cli/tests/thread-launch.test.mjs
index 0d207a0a0..fa3adb866 100644
--- a/packages/cli/tests/thread-launch.test.mjs
+++ b/packages/cli/tests/thread-launch.test.mjs
@@ -396,6 +396,22 @@ test("REQ-THREAD-1 REQ-LAUNCH-1 the chief can't launch the assistant outside a t
assert.deepEqual(launchLog(f).map((e) => [e.event, e.instance, e.code]), [["refused", "assistant", "thread-required"]]);
});
+// Admission refuses before bundle construction or a sandbox is needed.
+test('C2-09a: fromSession refuses a creative instance outside a thread without a sandbox', { timeout: 30000 }, async t => {
+ const prepared = prepare(t, { edit: doc => {
+ doc.roles.bean = { ...doc.roles.assistant, definition: 'companion' };
+ doc.launch.instances.push('bean');
+ return doc;
+ } });
+ const { f } = prepared;
+ const host = await start(t, prepared);
+ const chief = await host.host.bindLaunch({ business: 'acme', role: 'chief', run: 'chief-bean-refusal', harness: 'pi', pid: process.pid, startTime: startTimeOf(process.pid) });
+ await new Client({ path: host.host.path, cap: chief.cap }).call('role.claim');
+ assert.deepEqual(await host.launcher.fromSession(chief.cap, 'bean'), { ok: false, error: 'thread-required' });
+ assert.deepEqual(readSessions(f.dataRoot), []);
+ assert.deepEqual(launchLog(f).map(e => [e.event, e.instance, e.code]), [['refused', 'bean', 'thread-required']]);
+});
+
// Row 125 (#1619, REQ-LIMIT-3, REQ-LIMIT-4): the token-limit check switched on, with the
// assistant's limit at 0, so it is at its limit before any turn. The real check runs through the
// bus's plug-in loader.
@@ -443,3 +459,73 @@ test("REQ-LIMIT-4 a thread run at its token limit stops at the end of its turn:
assert.deepEqual(threadRuns(f, A), []);
assert.equal(host.runtime.threadsState("acme").find((x) => x.thread === A).holder, null);
});
+
+test('C2-09a: creative thread messages start distinct runs and keep each instance history separate', { skip, timeout: 90000 }, async t => {
+ const prepared = prepare(t, { sonnet: 2, idle: 60, edit: doc => {
+ const vars = { ...doc.roles.assistant.vars };
+ delete doc.roles.assistant;
+ doc.roles.bean = { definition: 'companion', vars: { ...vars } };
+ doc.roles.chet = { definition: 'continuity', vars: { ...vars } };
+ doc.launch.instances = ['coder', 'bean', 'chet'];
+ return doc;
+ } });
+ const host = await start(t, prepared), { f } = prepared;
+ const project = host.call('project.create', { name: 'Writing' }).id;
+ const bean = host.call('thread.create', { project, name: 'Bean', instance: 'bean' }).id;
+ const chet = host.call('thread.create', { project, name: 'Chet', instance: 'chet' }).id;
+ const send = async (thread, instance, body) => {
+ const message = host.call('thread.send', { thread, body });
+ const outcome = await until(() => host.call('thread.messages', { thread }).find(m => m.in_reply_to === message.id) ||
+ launchLog(f).find(row => row.thread === thread && row.event === 'refused'));
+ assert.notEqual(outcome.event, 'refused', `creative thread launch refused: ${outcome.code}`);
+ const reply = outcome;
+ assert.equal(reply.from_role, instance);
+ assert.equal(reply.to_role, 'human');
+ return JSON.parse(reply.body.match(/THREAD (\{.*\})/)[1]);
+ };
+ assert.deepEqual((await send(bean, 'bean', 'Bean input')).before, []);
+ assert.deepEqual((await send(chet, 'chet', 'Chet input')).before, []);
+ assert.deepEqual((await send(bean, 'bean', 'Bean again')).before, ['Bean input']);
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', bean, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === bean).session, 'session', 'history'), 'utf8'), 'Bean input\nBean again\n');
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', chet, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === chet).session, 'session', 'history'), 'utf8'), 'Chet input\n');
+ assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', bean, 'session')), false);
+ assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', chet, 'session')), false);
+ const launches = launchLog(f).filter(row => row.event === 'launch');
+ assert.ok(launches.some(row => row.instance === 'bean' && row.thread === bean));
+ assert.ok(launches.some(row => row.instance === 'chet' && row.thread === chet));
+ const chief = await host.host.bindLaunch({ business: 'acme', role: 'chief', run: 'chief-creative-test', harness: 'pi', pid: process.pid, startTime: startTimeOf(process.pid) });
+ await new Client({ path: host.host.path, cap: chief.cap }).call('role.claim');
+ assert.deepEqual(await host.launcher.fromSession(chief.cap, 'bean'), { ok: false, error: 'thread-required' });
+});
+
+test('C2-09a: terminating one creative thread does not signal an unselected peer of the same instance', { skip, timeout: 90000 }, async t => {
+ const prepared = prepare(t, { sonnet: 2, idle: 60, edit: doc => {
+ doc.roles.bean = { ...doc.roles.assistant, definition: 'companion' };
+ delete doc.roles.assistant;
+ doc.launch.instances = ['coder', 'bean'];
+ return doc;
+ } });
+ let requests = [];
+ const host = await start(t, prepared, { ops: () => ({
+ lifecycleRequests: () => requests,
+ lifecycleTake: () => ({ ...requests[0], go: true }),
+ lifecycleDone: () => { requests = []; return {}; },
+ }) });
+ const { f } = prepared;
+ const project = host.call('project.create', { name: 'Writing' }).id;
+ const threads = ['one', 'two'].map(name => host.call('thread.create', { project, name, instance: 'bean' }).id);
+ for (const thread of threads) {
+ const message = host.call('thread.send', { thread, body: 'Stay in this thread' });
+ const outcome = await until(() => host.call('thread.messages', { thread }).find(row => row.in_reply_to === message.id) ||
+ launchLog(f).find(row => row.thread === thread && row.event === 'refused'));
+ assert.notEqual(outcome.event, 'refused', `creative thread launch refused: ${outcome.code}`);
+ }
+ const runs = threads.map(thread => launchLog(f).find(row => row.thread === thread && row.event === 'launch').run);
+ requests = [{ request: 'one-thread-end', state: 'open', business: 'acme', action: 'lifecycle.end',
+ instance: 'bean', runs: [runs[0]], by: f.doc.human, at: new Date(Date.now() + 1000).toISOString() }];
+ await host.launcher.tick();
+ await until(() => launchLog(f).some(row => row.event === 'lifecycle-end' && row.run === runs[0]));
+ assert.deepEqual(launchLog(f).filter(row => row.event === 'lifecycle-end').map(row => row.run), [runs[0]]);
+ await until(() => !readSessions(f.dataRoot).some(row => row.run === runs[0]));
+ assert.ok(readSessions(f.dataRoot).some(row => row.run === runs[1]));
+});
diff --git a/packages/webui/src/chat-http.mjs b/packages/webui/src/chat-http.mjs
index c7770726d..396b42f3c 100644
--- a/packages/webui/src/chat-http.mjs
+++ b/packages/webui/src/chat-http.mjs
@@ -78,7 +78,8 @@ export async function chatHTTP(req, res, { path, search, chat, named, send, prev
(Object.hasOwn(v, 'repo') && (typeof v.repo !== 'string' || !KEY.test(v.repo)))) throw Error();
action = 'createProject'; args = v;
} else if (path === '/api/chat/threads') {
- if (!exact(v, ['project', 'name']) || !id(v.project) || !name(v.name)) throw Error();
+ if (!exact(v, ['project', 'name', 'instance'], ['project', 'name']) || !id(v.project) || !name(v.name) ||
+ (Object.hasOwn(v, 'instance') && (typeof v.instance !== 'string' || !KEY.test(v.instance)))) throw Error();
action = 'createThread'; args = v;
} else if (match?.[2] === 'messages') {
if (!exact(v, ['body']) || typeof v.body !== 'string' || !v.body.trim() || v.body.length > 32768) throw Error();
diff --git a/packages/webui/src/chat.mjs b/packages/webui/src/chat.mjs
index 018574ad4..65b89dab3 100644
--- a/packages/webui/src/chat.mjs
+++ b/packages/webui/src/chat.mjs
@@ -20,7 +20,7 @@ export function createChat({ call }) {
projects: () => channel('project.list', {}),
createProject: ({ name, repo }) => channel('project.create', { name, ...(repo === undefined ? {} : { repo }) }),
threads: ({ project } = {}) => channel('thread.list', project === undefined ? {} : { project }),
- createThread: ({ project, name }) => channel('thread.create', { project, name }),
+ createThread: ({ project, name, instance }) => channel('thread.create', { project, name, ...(instance === undefined ? {} : { instance }) }),
messages: ({ thread, after, limit }) => channel('thread.messages', { thread, ...(after ? { after } : {}), limit }),
send: ({ thread, body }) => channel('thread.send', { thread, body, class: 'REQUEST' }),
open: ({ thread }) => channel('thread.open', { thread }),
diff --git a/packages/webui/src/public/chat.js b/packages/webui/src/public/chat.js
index a6b805c1b..15066bdc6 100644
--- a/packages/webui/src/public/chat.js
+++ b/packages/webui/src/public/chat.js
@@ -14,7 +14,7 @@
return states.get(id);
};
const form = key => {
- if (!forms.has(key)) forms.set(key, { name: '', repo: '', receipt: '', pending: false });
+ if (!forms.has(key)) forms.set(key, { name: '', repo: '', instance: '', instanceChosen: false, receipt: '', pending: false });
return forms.get(key);
};
class ChatError extends Error {
@@ -58,7 +58,11 @@
function creation(kind, key) {
const f = form(key), project = kind === 'project';
const repo = project && current.repos.length ? `<label>Repository (optional)<select id="chat-repo" data-chat-field="repo"><option value="">No repository link</option>${current.repos.map(r => `<option value="${esc(r)}"${r === f.repo ? ' selected' : ''}>${txt(r)}</option>`).join('')}</select></label>` : '';
- return `<form id="chat-${kind}-form" class="chat-create" data-key="${esc(key)}"><h2>New ${kind}</h2><label>Name<input id="chat-${kind}-name" data-chat-field="name" value="${esc(f.name)}" maxlength="200" required${disabled(f.pending)}></label>${repo}<button class="btn" type="submit"${disabled(f.pending)}>${f.pending ? 'Creating…' : `Create ${kind}`}</button><p role="status">${txt(f.receipt)}</p></form>`;
+ const choices = current.instances ?? [];
+ const picker = project ? '' : `<label>Thread with<select id="chat-instance" data-chat-field="instance" required${disabled(f.pending || !!current.instanceError || !choices.length)}><option value="">Choose who this thread is with</option>${choices.map(row => `<option value="${esc(row.instance)}"${row.instance === f.instance ? ' selected' : ''}>${txt(row.name === row.instance ? row.instance : `${row.name} (${row.instance})`)}</option>`).join('')}</select></label>`;
+ const unavailable = !project && (!!current.instanceError || !choices.some(row => row.instance === f.instance));
+ const status = !project && current.instanceError ? current.instanceError : f.receipt || (!project && !choices.length ? 'No thread instances are configured.' : '');
+ return `<form id="chat-${kind}-form" class="chat-create" data-key="${esc(key)}"><h2>New ${kind}</h2><label>Name<input id="chat-${kind}-name" data-chat-field="name" value="${esc(f.name)}" maxlength="200" required${disabled(f.pending)}></label>${repo}${picker}<button class="btn" type="submit"${disabled(f.pending || unavailable)}>${f.pending ? 'Creating…' : `Create ${kind}`}</button><p role="status">${txt(status)}</p></form>`;
}
function threads(rows) {
return rows.length ? `<ul class="chat-thread-list">${rows.map(t => `<li>${link('threads', t.id, t.name)} <span class="muted">${txt(t.instance)}</span></li>`).join('')}</ul>` : '<p>No threads yet.</p>';
@@ -106,7 +110,7 @@
const f = document.getElementById(keep.field.id);
if (f && !f.disabled) {
f.focus({ preventScroll: true });
- if (keep.field.start !== null) f.setSelectionRange(keep.field.start, keep.field.end);
+ if (keep.field.start != null && typeof f.setSelectionRange === 'function') f.setSelectionRange(keep.field.start, keep.field.end);
}
} else if (navigated) c.container.querySelector('h1')?.focus({ preventScroll: true });
}
@@ -126,7 +130,7 @@
paint(); return;
}
const old = current;
- current = { container, kind, id, canSend, projects: old?.projects ?? [], threads: old?.threads ?? [], repos: old?.repos ?? [], error: '', refused: false };
+ current = { container, kind, id, canSend, projects: old?.projects ?? [], threads: old?.threads ?? [], repos: old?.repos ?? [], instances: old?.instances ?? [], instanceError: kind === 'project' ? 'Reading thread instances…' : '', error: '', refused: false };
if (navigated || !old) container.innerHTML = '<p class="chat-loading" role="status">Reading chat…</p>';
try {
const s = kind === 'thread' ? state(id) : null;
@@ -147,6 +151,25 @@
s.receipt = 'Message shown in this conversation.'; s.receiptId = null;
}
}
+ if (kind === 'project') {
+ try {
+ const listed = await request('instances', undefined, signal);
+ if (g !== generation || out()) return;
+ if (!listed.rows.every(row => typeof row?.instance === 'string' && /^[a-zA-Z0-9][a-zA-Z0-9_.-]{0,159}$/.test(row.instance) && typeof row.name === 'string'))
+ throw new ChatError('invalid-response');
+ current.instances = listed.rows; current.instanceError = '';
+ const f = form(id);
+ if (f.instance && !listed.rows.some(row => row.instance === f.instance)) {
+ f.instance = ''; f.instanceChosen = true;
+ f.receipt = 'The selected instance is no longer available. Choose who this thread is with.';
+ }
+ if (!f.instanceChosen && !f.instance && listed.rows.length === 1) f.instance = listed.rows[0].instance;
+ } catch (err) {
+ if (err.name === 'AbortError' || out() || g !== generation) return;
+ current.instances = [];
+ current.instanceError = "Couldn't read the thread instances; reload to try again";
+ }
+ }
// Repository choices are optional metadata; an unavailable read must not block unlinked chat.
if (kind === 'list') {
try {
@@ -179,7 +202,11 @@
if (!current || out()) return;
if (event.target.id === 'chat-body') state(current.id).draft = event.target.value;
const f = event.target.closest('.chat-create');
- if (f && event.target.dataset.chatField) form(f.dataset.key)[event.target.dataset.chatField] = event.target.value;
+ if (f && event.target.dataset.chatField) {
+ const draft = form(f.dataset.key), field = event.target.dataset.chatField;
+ draft[field] = event.target.value;
+ if (field === 'instance') { draft.instanceChosen = true; draft.receipt = ''; paint(); }
+ }
});
document.addEventListener('scroll', event => {
if (event.target.matches?.('.chat-log') && current?.kind === 'thread') {
@@ -232,7 +259,8 @@
void write('send', id, { body: state(id).draft }, `threads/${id}/messages`);
} else if (event.target.classList.contains('chat-create')) {
const key = event.target.dataset.key, f = form(key), project = key === 'projects';
- const value = project ? { name: f.name, ...(f.repo ? { repo: f.repo } : {}) } : { project: key, name: f.name };
+ if (!project && (current.instanceError || !(current.instances ?? []).some(row => row.instance === f.instance))) return;
+ const value = project ? { name: f.name, ...(f.repo ? { repo: f.repo } : {}) } : { project: key, name: f.name, instance: f.instance };
void write(project ? 'createProject' : 'createThread', key, value, project ? 'projects' : 'threads');
}
});
diff --git a/packages/webui/src/serve.mjs b/packages/webui/src/serve.mjs
index 288871d0c..d9d27a062 100644
--- a/packages/webui/src/serve.mjs
+++ b/packages/webui/src/serve.mjs
@@ -8,6 +8,7 @@ import { BusReadError, busStatus as coreBusStatus, subjectOk, sendOutcome } from
// Row 176, sage-1111: HTTP-only tester refusals; the row-164 transport pin stays untouched.
const busStatus = code => ['tester-off', 'tester-required'].includes(code) ? 403 : coreBusStatus(code);
import { ReadError, readStatus, fieldTable } from './reads.mjs';
+import { THREAD_DEFINITIONS } from '../../business/src/vocabulary.mjs';
import { chatHTTP } from './chat-http.mjs';
import { processingHTTP } from './processing-http.mjs';
@@ -705,6 +706,25 @@ export async function startServer({ host = '127.0.0.1', port = 7330, board = DEF
if (req.method !== 'POST') return json(res, 405, { error: 'method not allowed' });
return busSend(req, res, { send, preview: signer, log });
}
+ // Row 219: labels only, from this listener's own human or tester bus, after auth above.
+ if (path === '/api/chat/instances') {
+ if (req.method !== 'GET') return json(res, 405, { error: 'method-not-allowed' });
+ if (search) return json(res, 400, { error: 'invalid-request' });
+ if (!bus?.instances) return json(res, 503, { error: 'not-configured' });
+ try {
+ const value = await bus.instances();
+ if (!value || !value.instances || typeof value.instances !== 'object' || Array.isArray(value.instances))
+ throw new BusReadError('invalid-response');
+ const rows = Object.entries(value.instances)
+ .filter(([, entry]) => THREAD_DEFINITIONS.includes(entry?.definition))
+ .map(([instance, entry]) => ({ instance, name: entry.vars?.['persona.name'] || instance }));
+ if (rows.some(row => typeof row.name !== 'string')) throw new BusReadError('invalid-response');
+ return json(res, 200, { rows, at: new Date().toISOString() });
+ } catch (err) {
+ const code = err instanceof BusReadError ? err.code : 'invalid-response';
+ return json(res, busStatus(code), { error: code });
+ }
+ }
if (path === '/api/chat' || path.startsWith('/api/chat/')) {
return chatHTTP(req, res, { path, search, chat, named, send, preview: writer, log });
}
diff --git a/packages/webui/tests/chat-browser.test.mjs b/packages/webui/tests/chat-browser.test.mjs
index f3eeeca96..cc3ec093d 100644
--- a/packages/webui/tests/chat-browser.test.mjs
+++ b/packages/webui/tests/chat-browser.test.mjs
@@ -12,6 +12,7 @@ const HOSTILE = '<img src=x onerror="window.injected=1">\u001b[31m\u202eevil';
const stub = `(() => {
const real = fetch.bind(window);
window.__writes=[];window.__reads=[];window.__answers=[];window.__pages=[];
+ window.__instances=[{instance:'assistant',name:'assistant'}];
window.__projects=[{id:'${P}', name:${JSON.stringify(HOSTILE)}, repo:null},{id:'\"><img src=x>',name:'Invalid record'}];
window.__threads=[{id:'${A}',project:'${P}',name:'alpha',instance:'assistant'}, {id:'${B}',project:'${P}',name:'beta',instance:'assistant'}];
window.fetch=async (url,init={})=>{
@@ -33,6 +34,7 @@ const stub = `(() => {
window.__reads.push(path);
if(window.__holdRead && path.includes(window.__holdRead)){window.__heldSignal=init.signal;await new Promise(r=>window.__releaseRead=r);}
if(window.__readFailure)return new Response(JSON.stringify({error:window.__readFailure}),{status:window.__readFailure==='thread-not-owned'?403:503});
+ if(path==='/api/chat/instances')return window.__instanceFailure ? new Response(JSON.stringify({error:'not-configured'}),{status:503}) : data({rows:window.__instances});
if(path==='/api/chat/projects')return data({rows:window.__projects});
if(path.startsWith('/api/chat/threads')&&!path.includes('/messages'))return data({rows:window.__threads});
if(window.__pages.length)return data(window.__pages.shift());
@@ -82,7 +84,7 @@ test('chat browser: list/create named projects and threads, hostile labels inert
await b.evaluate(`window.__answers.push({body:{id:'${A}',instance:'assistant'}}),true`);
await click('#chat-thread-form button[type=submit]');
await wait('document.querySelector("#chat-send-form")');
- assert.deepEqual(await b.evaluate('window.__writes[1].body'), { project: P, name: 'named thread' });
+ assert.deepEqual(await b.evaluate('window.__writes[1].body'), { project: P, name: 'named thread', instance: 'assistant' });
assert.equal(await b.evaluate('window.__writes[1].path'), '/api/chat/threads');
assert.equal(await b.evaluate('window.__writes.length'), 2);
});
@@ -264,3 +266,65 @@ test('chat browser: a late project creation receipt cannot navigate away from an
assert.equal(await b.evaluate('location.hash'), '#/chat/threads/' + A);
assert.equal(await b.evaluate('document.querySelector("#chat-body").value'), 'stay in alpha');
});
+
+test('C2-09a picker: no silent choice, duplicate hostile labels stay inert, selection survives refresh and reaches POST', async t => {
+ const { b, wait, set, click, refresh } = await setup(t);
+ await b.evaluate(`window.__instances=[{instance:'bean',name:${JSON.stringify(HOSTILE)}},{instance:'chet',name:${JSON.stringify(HOSTILE)}}];location.hash='#/chat/projects/${P}';true`);
+ await wait('document.querySelectorAll("#chat-instance option").length===3');
+ assert.equal(await b.evaluate('document.querySelector("#chat-instance").value'), '');
+ assert.equal(await b.evaluate('document.querySelector("#chat-instance").required'), true);
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-form button").disabled'), true);
+ const labels = await b.evaluate('[...document.querySelectorAll("#chat-instance option")].map(o=>o.textContent)');
+ assert.match(labels[1], /\(bean\)/);
+ assert.match(labels[2], /\(chet\)/);
+ assert.doesNotMatch(labels.join(''), /[\u202a-\u202e\u2066-\u2069]/u);
+ assert.equal(await b.evaluate('!!document.querySelector("#chat-thread-form img")'), false);
+ assert.equal(await b.evaluate('window.injected'), undefined);
+ await set('#chat-thread-name', 'Bean discussion');
+ await click('#chat-thread-form button');
+ assert.equal(await b.evaluate('window.__writes.length'), 0);
+ await set('#chat-instance', 'bean');
+ await refresh();
+ assert.equal(await b.evaluate('document.querySelector("#chat-instance").value'), 'bean');
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-name").value'), 'Bean discussion');
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-form button").disabled'), false);
+ await b.evaluate(`window.__answers.push({body:{id:'${A}',instance:'bean'}});true`);
+ await click('#chat-thread-form button');
+ await wait('window.__writes.length===1');
+ assert.deepEqual(await b.evaluate('window.__writes[0]'), { path: '/api/chat/threads', body: { project: P, name: 'Bean discussion', instance: 'bean' }, redirect: 'manual' });
+});
+
+test('C2-09a picker: metadata failure, empty set and removed pick explain disabled state and recover without switching', async t => {
+ const { b, wait, set, refresh } = await setup(t);
+ await b.evaluate(`window.__instanceFailure=true;location.hash='#/chat/projects/${P}';true`);
+ await wait('document.querySelector("#chat-thread-form") && !document.querySelector(".chat-loading")');
+ assert.match(await b.evaluate('document.querySelector("#chat-thread-form [role=status]").textContent'), /read the thread instances/);
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-form button").disabled'), true);
+ await b.evaluate('window.__instanceFailure=false;window.__instances=[];true');
+ await refresh();
+ assert.match(await b.evaluate('document.querySelector("#chat-thread-form [role=status]").textContent'), /No thread instances/);
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-form button").disabled'), true);
+ await b.evaluate("window.__instances=[{instance:'bean',name:'Bean'},{instance:'chet',name:'Chet'}];true");
+ await refresh();
+ await set('#chat-instance', 'bean');
+ await b.evaluate("window.__instances=[{instance:'chet',name:'Chet'}];true");
+ await refresh();
+ assert.equal(await b.evaluate('document.querySelector("#chat-instance").value'), '');
+ assert.match(await b.evaluate('document.querySelector("#chat-thread-form [role=status]").textContent'), /no longer available/);
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-form button").disabled'), true);
+ await refresh();
+ assert.equal(await b.evaluate('document.querySelector("#chat-instance").value'), '', 'another refresh must not silently select the one remaining instance');
+ await set('#chat-instance', 'chet');
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-form button").disabled'), false);
+});
+
+test('C2-09a picker: a single instance is chosen explicitly but read-only mode cannot create a thread', async t => {
+ const { b, wait } = await setup(t, '?readonly');
+ await b.evaluate(`location.hash='#/chat/projects/${P}';true`);
+ await wait('document.querySelectorAll("#chat-instance option").length===2');
+ assert.equal(await b.evaluate('document.querySelector("#chat-instance").value'), 'assistant');
+ assert.equal(await b.evaluate('document.querySelector("#chat-instance").disabled'), true);
+ assert.equal(await b.evaluate('document.querySelector("#chat-thread-form button").disabled'), true);
+ assert.match(await b.evaluate('document.querySelector(".chat-area").textContent'), /only reads/);
+ assert.equal(await b.evaluate('window.__writes.length'), 0);
+});
diff --git a/packages/webui/tests/chat-instances.test.mjs b/packages/webui/tests/chat-instances.test.mjs
new file mode 100644
index 000000000..893c38f80
--- /dev/null
+++ b/packages/webui/tests/chat-instances.test.mjs
@@ -0,0 +1,87 @@
+import test from 'node:test';
+import assert from 'node:assert/strict';
+import { request } from 'node:http';
+import { mkdtempSync, rmSync } from 'node:fs';
+import { join } from 'node:path';
+import { tmpdir } from 'node:os';
+import { startServer } from '../src/serve.mjs';
+import { startTesterSocket, TESTER_ORIGIN } from '../src/tester-socket.mjs';
+import { close } from './fixture.mjs';
+
+const path = '/api/chat/instances';
+const preview = { host: 'chat.example', header: 'x-user', user: 'jason' };
+const snapshot = {
+ revision: 'a'.repeat(64), plugins: { private: 'do-not-project' },
+ instances: {
+ assistant: { definition: 'assistant', vars: { model: 'private-model' } },
+ bean: { definition: 'companion', vars: { 'persona.name': 'Bean', 'persona.sha256': 'private-hash' } },
+ chet: { definition: 'continuity', vars: { 'persona.name': 'Bean', file: '/private/path' } },
+ pm: { definition: 'pm', vars: { 'persona.name': 'Hidden PM' } },
+ },
+};
+function get(server, { route = path, method = 'GET', headers = {} } = {}) {
+ const address = server.address(), unix = typeof address === 'string';
+ return new Promise((resolve, reject) => {
+ const req = request({ ...(unix ? { socketPath: address } : { host: '127.0.0.1', port: address.port }),
+ path: route, method, headers: { host: unix ? new URL(TESTER_ORIGIN).host : preview.host, ...headers } }, res => {
+ let text = '';
+ res.on('data', chunk => text += chunk);
+ res.on('end', () => resolve({ status: res.statusCode, text, value: JSON.parse(text) }));
+ });
+ req.on('error', reject); req.end();
+ });
+}
+test('C2-09a metadata uses the human listener bus, projects labels only and refuses unauthenticated reads', async t => {
+ let calls = 0;
+ const server = await startServer({ port: 0, preview, bus: { instances: async () => { calls++; return snapshot; } } });
+ t.after(() => close(server));
+ const refused = await get(server);
+ assert.equal(refused.status, 401);
+ assert.equal(calls, 0);
+ const answer = await get(server, { headers: { 'x-user': 'jason' } });
+ assert.equal(answer.status, 200);
+ assert.deepEqual(answer.value.rows, [{ instance: 'assistant', name: 'assistant' }, { instance: 'bean', name: 'Bean' }, { instance: 'chet', name: 'Bean' }]);
+ for (const row of answer.value.rows) assert.deepEqual(Object.keys(row).sort(), ['instance', 'name']);
+ assert.doesNotMatch(answer.text, /private|Hidden PM/);
+ assert.equal(calls, 1);
+ for (const options of [{ route: path + '?extra=1' }, { method: 'POST' }]) {
+ const result = await get(server, { ...options, headers: { 'x-user': 'jason' } });
+ assert.ok([400, 405].includes(result.status));
+ }
+ assert.equal(calls, 1, 'invalid metadata requests never call a bus');
+});
+test('C2-09a metadata uses the private tester listener own bus and no human transport', async t => {
+ const root = mkdtempSync(join(tmpdir(), 'chat219-')); t.after(() => rmSync(root, { recursive: true, force: true }));
+ let reads = 0;
+ const server = await startTesterSocket({ dataRoot: root, board: 'http://127.0.0.1:9',
+ bus: { instances: async () => { reads++; return { instances: { quill: { definition: 'proofreader', vars: { 'persona.name': 'Quill' } } } }; } } });
+ t.after(() => close(server));
+ const answer = await get(server);
+ assert.equal(answer.status, 200);
+ assert.deepEqual(answer.value.rows, [{ instance: 'quill', name: 'Quill' }]);
+ assert.equal(reads, 1);
+});
+test('C2-09a metadata refuses missing or malformed reads and never echoes untrusted fields', async t => {
+ for (const bus of [null, { instances: async () => ({ instances: [] }) }, { instances: async () => { throw new Error('private-path'); } }]) {
+ const server = await startServer({ port: 0, preview, bus }); t.after(() => close(server));
+ const answer = await get(server, { headers: { 'x-user': 'jason' } });
+ assert.ok(answer.status >= 400);
+ assert.doesNotMatch(answer.text, /private-path/);
+ }
+});
+
+test('C2-09a metadata stays behind the SSO session check and a GET never refreshes session activity', async t => {
+ let session = null, reads = 0;
+ const touches = [];
+ const sso = { publicHost: 'sso-chat.example', publicOrigin: 'https://sso-chat.example', formTargets: () => [],
+ session: (_req, { touch }) => { touches.push(touch); return session; } };
+ const server = await startServer({ port: 0, sso, bus: { instances: async () => { reads++; return snapshot; } } });
+ t.after(() => close(server));
+ const headers = { host: sso.publicHost };
+ assert.equal((await get(server, { headers })).status, 401);
+ assert.equal(reads, 0);
+ session = { name: 'jason' };
+ assert.equal((await get(server, { headers })).status, 200);
+ assert.equal(reads, 1);
+ assert.deepEqual(touches, [false, false]);
+});
diff --git a/packages/webui/tests/chat.test.mjs b/packages/webui/tests/chat.test.mjs
index 8c11611cf..b47ecf1a7 100644
--- a/packages/webui/tests/chat.test.mjs
+++ b/packages/webui/tests/chat.test.mjs
@@ -335,3 +335,21 @@ test('the chat seam names the transport it is given: the human one and the teste
assert.throws(() => createChat({}), { name: 'TypeError', message: 'chat needs a bus transport function' });
assert.equal(typeof createChat({ call: async () => ({}) }).projects, 'function');
});
+
+test('C2-09a createThread forwards an explicit instance through the existing channel', async t => {
+ const c = await setup(t);
+ c.state.answer = { id: T, instance: 'bean' };
+ const answer = await c.get('/api/chat/threads', { method: 'POST', value: { project: P, name: 'Bean work', instance: 'bean' } });
+ assert.equal(answer.status, 200);
+ assert.deepEqual(c.calls, [['thread.create', { project: P, name: 'Bean work', instance: 'bean' }]]);
+ assert.equal(answer.data.instance, 'bean');
+});
+test('C2-09a malformed instance and extra thread fields refuse before the channel write', async t => {
+ const c = await setup(t);
+ for (const value of [null, 7, {}, [], '', 'bad name', 'bean/../../other']) {
+ const answer = await c.get('/api/chat/threads', { method: 'POST', value: { project: P, name: 'work', instance: value } });
+ assert.equal(answer.status, 400, JSON.stringify(value));
+ }
+ assert.equal((await c.get('/api/chat/threads', { method: 'POST', value: { project: P, name: 'work', instance: 'bean', extra: true } })).status, 400);
+ assert.deepEqual(c.calls, []);
+});
agents/rocko/work/queue-219/r2/candidate-manifest.sha256
+14
View File
@@ -0,0 +1,14 @@
142a210882535108159e045c61be288bc8703910a8ee0169137bc1eb80baff64 packages/bus/src/broker.mjs
b0c66c8999b567896923f6c876911dba936c6eca1ccc7aaeada51369fd613594 packages/bus/tests/creative.test.mjs
de4913f50801a11fd172e3f2c2b3cb41ab04e84d32a6650d1c8662b5e227ea3d packages/bus/tests/threads.test.mjs
8f7d6745fffb2a0898ac80c012084ac48964748da6439a8c56facc6529ffb19b packages/bus/tests/user-principal.test.mjs
b74275ce43249bafc97edc87a6a3aa0431c62fe1a28cd9fa265246e6d6da219b packages/cli/src/launcher.mjs
2c3f120dfdc0b52bf8ab38a88e86251be75d4b0d218e23df489dcaf815d6bc15 packages/cli/tests/launcher.test.mjs
7f308fdf601e839194f026beb3fea279eba1e356ce2756aa4a42fa4873b79b30 packages/cli/tests/thread-launch.test.mjs
cbfd54e6b375561d1e4679ee8d78a3285f970d9a7198cec9d22a06510a36afba packages/webui/src/chat-http.mjs
f49a49c6ec69783190d3f5eaf34316cb4d2c44d10d2ee9336fe1383207afefff packages/webui/src/chat.mjs
8e89df5fe8a9da35de41b5968afc6efcd92503e92ef28c6f557bb5371d10d1a4 packages/webui/src/public/chat.js
a597cc4902a873fe15650dacfce14dbc897db26310a7b6a24c293287add946c8 packages/webui/src/serve.mjs
d918e5b061ced9db28337a9b02c7042f9ddafaf09f32affce9f51190c0cba93f packages/webui/tests/chat-browser.test.mjs
2bad14535372488de326b82b791b79a61e1a4ab839458535132958ef85b746eb packages/webui/tests/chat-instances.test.mjs
7779d33d5b1dd3fe183722d0f91ff1f71e741e113cf2d5ee407f3d26428fc162 packages/webui/tests/chat.test.mjs
agents/rocko/work/queue-219/r2/changed-paths.txt
+14
View File
@@ -0,0 +1,14 @@
packages/bus/src/broker.mjs
packages/bus/tests/creative.test.mjs
packages/bus/tests/threads.test.mjs
packages/bus/tests/user-principal.test.mjs
packages/cli/src/launcher.mjs
packages/cli/tests/launcher.test.mjs
packages/cli/tests/thread-launch.test.mjs
packages/webui/src/chat-http.mjs
packages/webui/src/chat.mjs
packages/webui/src/public/chat.js
packages/webui/src/serve.mjs
packages/webui/tests/chat-browser.test.mjs
packages/webui/tests/chat-instances.test.mjs
packages/webui/tests/chat.test.mjs
agents/rocko/work/queue-219/r2/mos1420-test.diff
+17
View File
@@ -0,0 +1,17 @@
diff --git a/packages/cli/tests/thread-launch.test.mjs b/packages/cli/tests/thread-launch.test.mjs
index 84f8ed088..fa3adb866 100644
--- a/packages/cli/tests/thread-launch.test.mjs
+++ b/packages/cli/tests/thread-launch.test.mjs
@@ -486,8 +486,10 @@ test('C2-09a: creative thread messages start distinct runs and keep each instanc
assert.deepEqual((await send(bean, 'bean', 'Bean input')).before, []);
assert.deepEqual((await send(chet, 'chet', 'Chet input')).before, []);
assert.deepEqual((await send(bean, 'bean', 'Bean again')).before, ['Bean input']);
- assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', bean, 'session', 'history'), 'utf8'), 'Bean input\nBean again\n');
- assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', chet, 'session', 'history'), 'utf8'), 'Chet input\n');
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', bean, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === bean).session, 'session', 'history'), 'utf8'), 'Bean input\nBean again\n');
+ assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', chet, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === chet).session, 'session', 'history'), 'utf8'), 'Chet input\n');
+ assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', bean, 'session')), false);
+ assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', chet, 'session')), false);
const launches = launchLog(f).filter(row => row.event === 'launch');
assert.ok(launches.some(row => row.instance === 'bean' && row.thread === bean));
assert.ok(launches.some(row => row.instance === 'chet' && row.thread === chet));
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/cwd-sweep-final.json
+1
View File
@@ -0,0 +1 @@
[]
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/cwd-sweep.json
+1
View File
@@ -0,0 +1 @@
[]
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/head.json
+1
View File
@@ -0,0 +1 @@
{"head": "b97a3ff9757ec2ac39d9ab4cebb9769e471df932", "manifest": "a973912fe2fb9c64606cd99a385305b8f51498a096511b3a980bca6b0a5b98aa", "start": "2026-10-23T05:48:57.416807+00:00"}
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/network-cleanup.log
+2
View File
@@ -0,0 +1,2 @@
Error response from daemon: network rocko-r219-gate_default not found
exit status 1
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/results.jsonl
+4
View File
@@ -0,0 +1,4 @@
{"label": "single-bus-creative.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/creative.test.mjs"], "start": "2026-10-23T05:48:57.418927+00:00", "end": "2026-10-23T05:48:57.834246+00:00", "seconds": 0.415, "exit": 0, "timeout": false, "counts": {"tests": 4, "pass": 4, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-creative.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rs156uowe"}
{"label": "single-bus-threads.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/threads.test.mjs"], "start": "2026-10-23T05:48:57.835837+00:00", "end": "2026-10-23T05:48:59.152912+00:00", "seconds": 1.317, "exit": 0, "timeout": false, "counts": {"tests": 19, "pass": 19, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-threads.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rbqz65jtz"}
{"label": "single-bus-user-principal.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/user-principal.test.mjs"], "start": "2026-10-23T05:48:59.154288+00:00", "end": "2026-10-23T05:48:59.719646+00:00", "seconds": 0.565, "exit": 0, "timeout": false, "counts": {"tests": 23, "pass": 23, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-user-principal.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rztf343rx"}
{"label": "single-cli-launcher.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/cli/tests/launcher.test.mjs"], "start": "2026-10-23T05:48:59.721051+00:00", "end": "2026-10-23T05:49:26.296570+00:00", "seconds": 26.576, "exit": 1, "timeout": false, "counts": {"tests": 34, "pass": 33, "fail": 1, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-cli-launcher.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/r8xucbjgl"}
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-bus-creative.test.tap
+36
View File
@@ -0,0 +1,36 @@
TAP version 13
# organization: {"event":"reload-needs-restart","business":"demo"}
# organization: {"event":"reload-needs-restart","business":"demo"}
# Subtest: M6: a creative raise refuses decision-not-allowed, cited or not, and no decision row appears; the assistant still raises
ok 1 - M6: a creative raise refuses decision-not-allowed, cited or not, and no decision row appears; the assistant still raises
---
duration_ms: 37.235384
type: 'test'
...
# Subtest: a creative instance sends only to the user and hears only from the user
ok 2 - a creative instance sends only to the user and hears only from the user
---
duration_ms: 44.266739
type: 'test'
...
# Subtest: M10 through the broker: the chief and the tester are refused on bean, the human's limits.set of its models key works
ok 3 - M10 through the broker: the chief and the tester are refused on bean, the human's limits.set of its models key works
---
duration_ms: 83.079495
type: 'test'
...
# Subtest: row 256 T6 the human deletes a creative instance through the broker; the chief and the tester are refused at the verb
ok 4 - row 256 T6 the human deletes a creative instance through the broker; the chief and the tester are refused at the verb
---
duration_ms: 63.576082
type: 'test'
...
1..4
# tests 4
# suites 0
# pass 4
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 356.82109
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-bus-threads.test.tap
+124
View File
@@ -0,0 +1,124 @@
TAP version 13
# Subtest: REQ-ROLE-2 REQ-THREAD-1: one holder per thread, through the broker and the trigger
ok 1 - REQ-ROLE-2 REQ-THREAD-1: one holder per thread, through the broker and the trigger
---
duration_ms: 37.957781
type: 'test'
...
# Subtest: REQ-ROLE-2 REQ-THREAD-1: the 3e triggers refuse writes that skip the broker
ok 2 - REQ-ROLE-2 REQ-THREAD-1: the 3e triggers refuse writes that skip the broker
---
duration_ms: 68.301373
type: 'test'
...
# Subtest: REQ-MSG-1: a message to or from the assistant names its thread, or is refused
ok 3 - REQ-MSG-1: a message to or from the assistant names its thread, or is refused
---
duration_ms: 31.316512
type: 'test'
...
# Subtest: REQ-MSG-1: the chief of staff's reply comes back to the thread that sent the work
ok 4 - REQ-MSG-1: the chief of staff's reply comes back to the thread that sent the work
---
duration_ms: 593.922455
type: 'test'
...
# Subtest: REQ-MSG-1: a reply can't carry one thread instance's thread to another thread instance
ok 5 - REQ-MSG-1: a reply can't carry one thread instance's thread to another thread instance
---
duration_ms: 24.857971
type: 'test'
...
# Subtest: REQ-THREAD-1 REQ-USER-2: one thread's messages never reach another thread's holder
ok 6 - REQ-THREAD-1 REQ-USER-2: one thread's messages never reach another thread's holder
---
duration_ms: 27.519976
type: 'test'
...
# Subtest: REQ-LAUNCH-1: a message to a thread with no holder waits, and the next holder gets it
ok 7 - REQ-LAUNCH-1: a message to a thread with no holder waits, and the next holder gets it
---
duration_ms: 30.716822
type: 'test'
...
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1: threadIdle releases only a thread with nothing waiting, and only for its holder
ok 8 - REQ-THREAD-2 REQ-LAUNCH-1: threadIdle releases only a thread with nothing waiting, and only for its holder
---
duration_ms: 33.754906
type: 'test'
...
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1: a message delivered to a run that ended unread doesn't hold up the next holder
ok 9 - REQ-THREAD-2 REQ-LAUNCH-1: a message delivered to a run that ended unread doesn't hold up the next holder
---
duration_ms: 29.046481
type: 'test'
...
# Subtest: REQ-ROLE-2 REQ-THREAD-1 Q169: a role.revoke the human approved ends every thread run of the assistant
ok 10 - REQ-ROLE-2 REQ-THREAD-1 Q169: a role.revoke the human approved ends every thread run of the assistant
---
duration_ms: 26.449042
type: 'test'
...
# Subtest: Q169 REQ-USER-2: assistant.stop ends the human's own assistant thread runs, and only the human's
ok 11 - Q169 REQ-USER-2: assistant.stop ends the human's own assistant thread runs, and only the human's
---
duration_ms: 38.524966
type: 'test'
...
# Subtest: REQ-USER-2: the human verbs refuse another owner's thread
ok 12 - REQ-USER-2: the human verbs refuse another owner's thread
---
duration_ms: 28.558392
type: 'test'
...
# Subtest: REQ-THREAD-1: thread.create refuses when the business has no thread instance or more than one
ok 13 - REQ-THREAD-1: thread.create refuses when the business has no thread instance or more than one
---
duration_ms: 23.166467
type: 'test'
...
# Subtest: REQ-ORG-2: projects and threads are named once, and the repo names a business project
ok 14 - REQ-ORG-2: projects and threads are named once, and the repo names a business project
---
duration_ms: 28.154835
type: 'test'
...
# Subtest: REQ-THREAD-2: thread.messages returns the thread's history in pages and writes nothing
ok 15 - REQ-THREAD-2: thread.messages returns the thread's history in pages and writes nothing
---
duration_ms: 86.802213
type: 'test'
...
# Subtest: project.create refuses a repository name without its matching repo before any write
ok 16 - project.create refuses a repository name without its matching repo before any write
---
duration_ms: 15.244016
type: 'test'
...
# Subtest: project.create keeps unrelated names with and without a repository
ok 17 - project.create keeps unrelated names with and without a repository
---
duration_ms: 11.57841
type: 'test'
...
# Subtest: C2-09a: explicit creative instances bind independent threads, default sessions and holders
ok 18 - C2-09a: explicit creative instances bind independent threads, default sessions and holders
---
duration_ms: 46.82113
type: 'test'
...
# Subtest: C2-09a: explicit missing, non-thread and malformed selectors create no thread or session
ok 19 - C2-09a: explicit missing, non-thread and malformed selectors create no thread or session
---
duration_ms: 20.263528
type: 'test'
...
1..19
# tests 19
# suites 0
# pass 19
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 1283.575562
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-bus-user-principal.test.tap
+148
View File
@@ -0,0 +1,148 @@
TAP version 13
# Subtest: R3: bindUser binds a granted user and refuses one with no live grant
ok 1 - R3: bindUser binds a granted user and refuses one with no live grant
---
duration_ms: 15.216913
type: 'test'
...
# Subtest: R3: a user named like the business human, the tester or a principal word is refused, whatever the grants say
ok 2 - R3: a user named like the business human, the tester or a principal word is refused, whatever the grants say
---
duration_ms: 10.127905
type: 'test'
...
# Subtest: R3: each collaborator verb is allowed to a granted user
ok 3 - R3: each collaborator verb is allowed to a granted user
---
duration_ms: 18.491408
type: 'test'
...
# Subtest: R3: every verb off the collaborator list refuses a user access-refused before its own checks
ok 4 - R3: every verb off the collaborator list refuses a user access-refused before its own checks
---
duration_ms: 95.840429
type: 'test'
...
# Subtest: R3: task, web and host verbs refuse a user access-refused
ok 5 - R3: task, web and host verbs refuse a user access-refused
---
duration_ms: 22.333602
type: 'test'
...
# Subtest: R3 leak: project.list shows granted projects only
ok 6 - R3 leak: project.list shows granted projects only
---
duration_ms: 12.494935
type: 'test'
...
# Subtest: R3 leak: thread.create needs the project and the thread instance granted, and an ungranted id reads as one that does not exist
ok 7 - R3 leak: thread.create needs the project and the thread instance granted, and an ungranted id reads as one that does not exist
---
duration_ms: 15.195921
type: 'test'
...
# Subtest: R3 leak: thread.list shows the user its own threads that are still granted, never others
ok 8 - R3 leak: thread.list shows the user its own threads that are still granted, never others
---
duration_ms: 33.037437
type: 'test'
...
# Subtest: R3 leak: names shows granted instances only
ok 9 - R3 leak: names shows granted instances only
---
duration_ms: 14.891286
type: 'test'
...
# Subtest: R3: thread.send is from user:<id> and writes no human.input
ok 10 - R3: thread.send is from user:<id> and writes no human.input
---
duration_ms: 13.366772
type: 'test'
...
# Subtest: R3: a reply-chain message.send into another user thread is refused
ok 11 - R3: a reply-chain message.send into another user thread is refused
---
duration_ms: 15.523733
type: 'test'
...
# Subtest: R3: the run reply to a user message reaches that user thread.messages, with no waiting and no notice
ok 12 - R3: the run reply to a user message reaches that user thread.messages, with no waiting and no notice
---
duration_ms: 18.163702
type: 'test'
...
# Subtest: R3: a reply to: user without a matching in_reply_to is refused user-reply-required
ok 13 - R3: a reply to: user without a matching in_reply_to is refused user-reply-required
---
duration_ms: 26.445744
type: 'test'
...
# Subtest: R3: a non-thread run, the human and the tester cannot send to: user
ok 14 - R3: a non-thread run, the human and the tester cannot send to: user
---
duration_ms: 17.29104
type: 'test'
...
# Subtest: R3: a user thread run cannot message the owner, while its uncited gated raise reaches only the owner inbox, B9
ok 15 - R3: a user thread run cannot message the owner, while its uncited gated raise reaches only the owner inbox, B9
---
duration_ms: 19.258704
type: 'test'
...
# Subtest: R3: a removed or expired grant refuses the next request access-revoked, and the file is read per request
ok 16 - R3: a removed or expired grant refuses the next request access-revoked, and the file is read per request
---
duration_ms: 18.231409
type: 'test'
...
# Subtest: R3: a user refusal is recorded as action.refused by user:<id>
ok 17 - R3: a user refusal is recorded as action.refused by user:<id>
---
duration_ms: 13.797301
type: 'test'
...
# Subtest: R3: a business with a role keyed user refuses invalid-business
ok 18 - R3: a business with a role keyed user refuses invalid-business
---
duration_ms: 9.468564
type: 'test'
...
# Subtest: R3: name.set refuses the name user
ok 19 - R3: name.set refuses the name user
---
duration_ms: 9.752458
type: 'test'
...
# Subtest: R3 r4: while halted, a granted user's thread.send refuses processing-halted and thread.messages still answers
ok 20 - R3 r4: while halted, a granted user's thread.send refuses processing-halted and thread.messages still answers
---
duration_ms: 13.617784
type: 'test'
...
# Subtest: R3 r4: the chief's hire refuses an instance named user with the code it gives human and tester
ok 21 - R3 r4: the chief's hire refuses an instance named user with the code it gives human and tester
---
duration_ms: 14.726171
type: 'test'
...
# Subtest: R3 r4: a non-function access throws before the store is read
ok 22 - R3 r4: a non-function access throws before the store is read
---
duration_ms: 0.105564
type: 'test'
...
# Subtest: C2-09a: naming an instance cannot bypass its collaborator grant or disclose an ungranted project
ok 23 - C2-09a: naming an instance cannot bypass its collaborator grant or disclose an ungranted project
---
duration_ms: 15.883063
type: 'test'
...
1..23
# tests 23
# suites 0
# pass 23
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 523.149354
agents/rocko/work/queue-219/run-4a9c-mos1408-red-before-mos1418/single-cli-launcher.test.tap
+259
View File
@@ -0,0 +1,259 @@
TAP version 13
# Subtest: C2-04: launcher workspace clones code but never the library
ok 1 - C2-04: launcher workspace clones code but never the library
---
duration_ms: 1444.885132
type: 'test'
...
# Subtest: bus start --pm: the launcher instance (the chief of staff) runs under its own PID namespace, registered, with a manifest
ok 2 - bus start --pm: the launcher instance (the chief of staff) runs under its own PID namespace, registered, with a manifest
---
duration_ms: 1312.408111
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r910aab09c0d6","instance":"chief","turn":"368e3045-8783-47d3-8ae1-e429b321d9b1","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r5bb5f0657d94","instance":"coder","turn":"3432d01f-ca94-4a5e-88d3-19588a40a81d","source":"@none","code":"baseline-unknown"}
# Subtest: the chief of staff launches a coder through its launch tool; the coder answers; refusals name their code
ok 3 - the chief of staff launches a coder through its launch tool; the coder answers; refusals name their code
---
duration_ms: 745.868459
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"3bd3e4d7-3af4-4a1c-99f1-a8f25b7ab1dd","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"b2db478d-2905-49fd-a81a-0800643bed6a","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"ac2aa380-f3a0-40d4-960f-a543acb8c431","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"e8b5124b-591b-4d5b-829c-e944bb3e24bb","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"6a6e1fa4-5182-42dc-bbc2-26f136eedee3","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"54eb77b5-3880-4afb-9772-0b9d590eb328","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"11fe8b92-1dae-416a-838b-ae305db74bc6","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"68266357-b477-433c-99ed-f1af37143d91","source":"@none","code":"baseline-unknown"}
# Subtest: a launched pm's request_staff reaches the chief of staff; no other session has the tool and the launch limits still hold
ok 4 - a launched pm's request_staff reaches the chief of staff; no other session has the tool and the launch limits still hold
---
duration_ms: 1245.265675
type: 'test'
...
# Subtest: each launch makes sure the workspace has a clone of the project: cloned, fast-forwarded, or fetched and logged
ok 5 - each launch makes sure the workspace has a clone of the project: cloned, fast-forwarded, or fetched and logged
---
duration_ms: 4072.119958
type: 'test'
...
# Subtest: a role the broker says holds a merge decision gets land_work, its prompt line, its landing and the git socket; without it, none
ok 6 - a role the broker says holds a merge decision gets land_work, its prompt line, its landing and the git socket; without it, none
---
duration_ms: 621.888037
type: 'test'
...
# Subtest: REQ-LAUNCH-1 the tick starts a listed merge decision holder once, with land_work, the Landing line and its landing turn; an unlisted holder starts nothing
ok 7 - REQ-LAUNCH-1 the tick starts a listed merge decision holder once, with land_work, the Landing line and its landing turn; an unlisted holder starts nothing
---
duration_ms: 417.133166
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r8e91dd37dc4b","instance":"coder","turn":"a7b24e30-ac5e-47cf-a951-90cf0d948b4d","source":"@none","code":"baseline-unknown"}
# Subtest: a holder running since before the resolution is stopped once the broker releases it, land-relaunch, and the next tick starts it: landing turn first, then the message that waited
ok 8 - a holder running since before the resolution is stopped once the broker releases it, land-relaunch, and the next tick starts it: landing turn first, then the message that waited
---
duration_ms: 730.904044
type: 'test'
...
# Subtest: a landing run that ended isn't started again for its decision, a spent decision starts nothing, and a new decision starts the holder
ok 9 - a landing run that ended isn't started again for its decision, a spent decision starts nothing, and a new decision starts the holder
---
duration_ms: 698.470719
type: 'test'
...
# Subtest: after a restart, the new host's first tick starts a holder whose decision is still held
ok 10 - after a restart, the new host's first tick starts a holder whose decision is still held
---
duration_ms: 920.432738
type: 'test'
...
# Subtest: a refused landing start is logged once per code with its decision, isn't a start, and the next tick with room starts the holder
ok 11 - a refused landing start is logged once per code with its decision, isn't a start, and the next tick with room starts the holder
---
duration_ms: 641.309798
type: 'test'
...
# Subtest: a project clone that can't be made refuses checkout-failed, from --chief and from a session, with no run and no clone left
ok 12 - a project clone that can't be made refuses checkout-failed, from --chief and from a session, with no run and no clone left
---
duration_ms: 267.647539
type: 'test'
...
# Subtest: a runner that stops at once ends its launch with the runner's reason
ok 13 - a runner that stops at once ends its launch with the runner's reason
---
duration_ms: 332.423482
type: 'test'
...
# Subtest: a Claude Code launch with no session credential refuses before it starts
ok 14 - a Claude Code launch with no session credential refuses before it starts
---
duration_ms: 181.931254
type: 'test'
...
# Subtest: a pi launch needs no session credential: pi logs in through its own ENV_ALLOW variables
ok 15 - a pi launch needs no session credential: pi logs in through its own ENV_ALLOW variables
---
duration_ms: 315.27683
type: 'test'
...
# usage: {"event":"plugin-refused","kind":"harness","name":"down","code":"missing","message":"/mnt/storage/scratch/rocko-r219/packages/plugins/harness/down is missing","kept":[]}
# plugins: {"event":"plugin-refused","kind":"harness","name":"down","code":"missing","message":"/mnt/storage/scratch/rocko-r219/packages/plugins/harness/down is missing","kept":[]}
# Subtest: row 65 a failed primary preflight launches the fallback on a fixture harness module, recording the route and the reason
ok 16 - row 65 a failed primary preflight launches the fallback on a fixture harness module, recording the route and the reason
---
duration_ms: 353.028786
type: 'test'
...
# Subtest: a runner killed from the host ends its launch as killed, not failed
ok 17 - a runner killed from the host ends its launch as killed, not failed
---
duration_ms: 375.548364
type: 'test'
...
# Subtest: a missing or failing bwrap refuses sandbox-unavailable before anything starts; there is no unconfined fallback
ok 18 - a missing or failing bwrap refuses sandbox-unavailable before anything starts; there is no unconfined fallback
---
duration_ms: 187.871873
type: 'test'
...
# Subtest: row 64 a role skill that isn't enabled refuses skill-not-enabled, and one that isn't a plain directory skill-refused, before anything starts
ok 19 - row 64 a role skill that isn't enabled refuses skill-not-enabled, and one that isn't a plain directory skill-refused, before anything starts
---
duration_ms: 187.807189
type: 'test'
...
# Subtest: row 213 a creative instance's persona is read from <configDir>/personas: off its digest the launch fails with the mismatch as its reason
not ok 20 - row 213 a creative instance's persona is read from <configDir>/personas: off its digest the launch fails with the mismatch as its reason
---
duration_ms: 255.698016
type: 'test'
location: '/mnt/storage/scratch/rocko-r219/packages/cli/tests/launcher.test.mjs:766:1'
failureType: 'testCodeFailure'
error: |-
Expected values to be strictly deep-equal:
+ actual - expected
[
+ 'compactions',
+ undefined,
+ 2
- 'refused',
- 'launch-failed',
- 1
]
code: 'ERR_ASSERTION'
name: 'AssertionError'
expected:
0: 'refused'
1: 'launch-failed'
2: 1
actual:
0: 'compactions'
2: 2
operator: 'deepStrictEqual'
stack: |-
TestContext.<anonymous> (file:///mnt/storage/scratch/rocko-r219/packages/cli/tests/launcher.test.mjs:789:10)
process.processTicksAndRejections (node:internal/process/task_queues:104:5)
async Test.run (node:internal/test_runner/test:1409:7)
async Test.processPendingSubtests (node:internal/test_runner/test:974:7)
...
# Subtest: row 64 on Claude Code a role skill that isn't enabled refuses the same way, before anything starts
ok 21 - row 64 on Claude Code a role skill that isn't enabled refuses the same way, before anything starts
---
duration_ms: 194.030218
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r3715d40bd7fb","instance":"chief","turn":"4c85d22f-fdab-4ab7-ad8a-6b4c4d1fbf72","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r16ae936abadf","instance":"coder","turn":"2c6b06f1-8f36-4261-81b7-2689b9bb7ff4","source":"@none","code":"baseline-unknown"}
# Subtest: a real Claude Code coder's shell can't read a stand-in secret or anything else its sandbox doesn't hold
ok 22 - a real Claude Code coder's shell can't read a stand-in secret or anything else its sandbox doesn't hold
---
duration_ms: 1456.773218
type: 'test'
...
# Subtest: a host that died hard leaves its sessions to the next host, which kills them and ends their runs so the role can be launched again
ok 23 - a host that died hard leaves its sessions to the next host, which kills them and ends their runs so the role can be launched again
---
duration_ms: 1063.59923
type: 'test'
...
# Subtest: a host that died hard leaves its sessions to the next host, which finds one already exited (23) and ends their runs so the role can be launched again
ok 24 - a host that died hard leaves its sessions to the next host, which finds one already exited (23) and ends their runs so the role can be launched again
---
duration_ms: 4016.888246
type: 'test'
...
# Subtest: bus start --no-launch leaves an earlier host's live session alone: no signal, no end, sessions.json as it was
ok 25 - bus start --no-launch leaves an earlier host's live session alone: no signal, no end, sessions.json as it was
---
duration_ms: 237.364574
type: 'test'
...
# Subtest: bus start --no-launch refuses every launch: the PM launch and a session's request, each logged, nothing spawned
ok 26 - bus start --no-launch refuses every launch: the PM launch and a session's request, each logged, nothing spawned
---
duration_ms: 197.775267
type: 'test'
...
# Subtest: bus start --no-launch starts no thread tick; the same host with launches runs it
ok 27 - bus start --no-launch starts no thread tick; the same host with launches runs it
---
duration_ms: 1181.987654
type: 'test'
...
# Subtest: a malformed sessions.json refuses the host start with exit 3 and stays as it was
ok 28 - a malformed sessions.json refuses the host start with exit 3 and stays as it was
---
duration_ms: 177.111363
type: 'test'
...
# Subtest: an over-long launch request is refused at once, not at the 10 s idle timeout
ok 29 - an over-long launch request is refused at once, not at the 10 s idle timeout
---
duration_ms: 183.364128
type: 'test'
...
# Subtest: a launch client that never closes its side doesn't hold the host's close
ok 30 - a launch client that never closes its side doesn't hold the host's close
---
duration_ms: 179.49662
type: 'test'
...
# Subtest: a runner that ignores SIGTERM is killed when the host closes
ok 31 - a runner that ignores SIGTERM is killed when the host closes
---
duration_ms: 1352.083242
type: 'test'
...
# Subtest: kill switch refuses chief and hire before launch work and a clear permits a later request
ok 32 - kill switch refuses chief and hire before launch work and a clear permits a later request
---
duration_ms: 319.505559
type: 'test'
...
# Subtest: kill switch stops an actual managed namespace and records the halt reason without rewriting its bundle
ok 33 - kill switch stops an actual managed namespace and records the halt reason without rewriting its bundle
---
duration_ms: 334.076309
type: 'test'
...
# Subtest: a launch waiting across halt and resume cannot use its stale admission
ok 34 - a launch waiting across halt and resume cannot use its stale admission
---
duration_ms: 201.932098
type: 'test'
...
1..34
# tests 34
# suites 0
# pass 33
# fail 1
# cancelled 0
# skipped 0
# todo 0
# duration_ms 26522.233904
agents/rocko/work/queue-219/run-4a9c-mos1408/head.json
+1 -1
View File
@@ -1 +1 @@
{"head": "b97a3ff9757ec2ac39d9ab4cebb9769e471df932", "manifest": "a973912fe2fb9c64606cd99a385305b8f51498a096511b3a980bca6b0a5b98aa", "start": "2026-10-23T05:48:57.416807+00:00"}
{"head": "7cbd839d037f711de136108882b53597cf16d742", "manifest": "84a8bd9afc5420fc315586584aec91258a28bd728000dcd2cb61ac41b2fe711a", "start": "2026-10-23T06:09:43.704053+00:00"}
agents/rocko/work/queue-219/run-4a9c-mos1408/results.jsonl
+5 -4
View File
@@ -1,4 +1,5 @@
{"label": "single-bus-creative.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/creative.test.mjs"], "start": "2026-10-23T05:48:57.418927+00:00", "end": "2026-10-23T05:48:57.834246+00:00", "seconds": 0.415, "exit": 0, "timeout": false, "counts": {"tests": 4, "pass": 4, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-creative.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rs156uowe"}
{"label": "single-bus-threads.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/threads.test.mjs"], "start": "2026-10-23T05:48:57.835837+00:00", "end": "2026-10-23T05:48:59.152912+00:00", "seconds": 1.317, "exit": 0, "timeout": false, "counts": {"tests": 19, "pass": 19, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-threads.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rbqz65jtz"}
{"label": "single-bus-user-principal.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/user-principal.test.mjs"], "start": "2026-10-23T05:48:59.154288+00:00", "end": "2026-10-23T05:48:59.719646+00:00", "seconds": 0.565, "exit": 0, "timeout": false, "counts": {"tests": 23, "pass": 23, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-user-principal.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rztf343rx"}
{"label": "single-cli-launcher.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/cli/tests/launcher.test.mjs"], "start": "2026-10-23T05:48:59.721051+00:00", "end": "2026-10-23T05:49:26.296570+00:00", "seconds": 26.576, "exit": 1, "timeout": false, "counts": {"tests": 34, "pass": 33, "fail": 1, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-cli-launcher.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/r8xucbjgl"}
{"label": "single-bus-creative.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/creative.test.mjs"], "start": "2026-10-23T06:09:43.706182+00:00", "end": "2026-10-23T06:09:44.121877+00:00", "seconds": 0.416, "exit": 0, "timeout": false, "counts": {"tests": 4, "pass": 4, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-creative.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rmc2uerc6"}
{"label": "single-bus-threads.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/threads.test.mjs"], "start": "2026-10-23T06:09:44.123566+00:00", "end": "2026-10-23T06:09:45.490657+00:00", "seconds": 1.367, "exit": 0, "timeout": false, "counts": {"tests": 19, "pass": 19, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-threads.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rismt3po4"}
{"label": "single-bus-user-principal.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/bus/tests/user-principal.test.mjs"], "start": "2026-10-23T06:09:45.492192+00:00", "end": "2026-10-23T06:09:46.107814+00:00", "seconds": 0.616, "exit": 0, "timeout": false, "counts": {"tests": 23, "pass": 23, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-user-principal.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/repq8xlqh"}
{"label": "single-cli-launcher.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/cli/tests/launcher.test.mjs"], "start": "2026-10-23T06:09:46.109200+00:00", "end": "2026-10-23T06:10:12.635877+00:00", "seconds": 26.527, "exit": 0, "timeout": false, "counts": {"tests": 34, "pass": 34, "fail": 0, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-cli-launcher.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rkqztfjx8"}
{"label": "single-cli-thread-launch.test", "args": ["timeout", "-k", "10", "300", "node", "--test-reporter=tap", "--test", "packages/cli/tests/thread-launch.test.mjs"], "start": "2026-10-23T06:10:12.637449+00:00", "end": "2026-10-23T06:10:30.695792+00:00", "seconds": 18.058, "exit": 1, "timeout": false, "counts": {"tests": 14, "pass": 13, "fail": 1, "cancelled": 0, "skipped": 0}, "skips": ["# skipped 0"], "log": "agents/rocko/work/queue-219/run-4a9c-mos1408/single-cli-thread-launch.test.tap", "tmpdir": "/mnt/storage/scratch/tmp/rbyz9a6iu"}
agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-creative.test.tap
+5 -5
View File
@@ -4,25 +4,25 @@ TAP version 13
# Subtest: M6: a creative raise refuses decision-not-allowed, cited or not, and no decision row appears; the assistant still raises
ok 1 - M6: a creative raise refuses decision-not-allowed, cited or not, and no decision row appears; the assistant still raises
---
duration_ms: 37.235384
duration_ms: 43.416235
type: 'test'
...
# Subtest: a creative instance sends only to the user and hears only from the user
ok 2 - a creative instance sends only to the user and hears only from the user
---
duration_ms: 44.266739
duration_ms: 43.274527
type: 'test'
...
# Subtest: M10 through the broker: the chief and the tester are refused on bean, the human's limits.set of its models key works
ok 3 - M10 through the broker: the chief and the tester are refused on bean, the human's limits.set of its models key works
---
duration_ms: 83.079495
duration_ms: 76.669863
type: 'test'
...
# Subtest: row 256 T6 the human deletes a creative instance through the broker; the chief and the tester are refused at the verb
ok 4 - row 256 T6 the human deletes a creative instance through the broker; the chief and the tester are refused at the verb
---
duration_ms: 63.576082
duration_ms: 60.418493
type: 'test'
...
1..4
@@ -33,4 +33,4 @@ ok 4 - row 256 T6 the human deletes a creative instance through the broker; the
# cancelled 0
# skipped 0
# todo 0
# duration_ms 356.82109
# duration_ms 374.784911
agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-threads.test.tap
+20 -20
View File
@@ -2,115 +2,115 @@ TAP version 13
# Subtest: REQ-ROLE-2 REQ-THREAD-1: one holder per thread, through the broker and the trigger
ok 1 - REQ-ROLE-2 REQ-THREAD-1: one holder per thread, through the broker and the trigger
---
duration_ms: 37.957781
duration_ms: 37.977187
type: 'test'
...
# Subtest: REQ-ROLE-2 REQ-THREAD-1: the 3e triggers refuse writes that skip the broker
ok 2 - REQ-ROLE-2 REQ-THREAD-1: the 3e triggers refuse writes that skip the broker
---
duration_ms: 68.301373
duration_ms: 68.5376
type: 'test'
...
# Subtest: REQ-MSG-1: a message to or from the assistant names its thread, or is refused
ok 3 - REQ-MSG-1: a message to or from the assistant names its thread, or is refused
---
duration_ms: 31.316512
duration_ms: 33.043064
type: 'test'
...
# Subtest: REQ-MSG-1: the chief of staff's reply comes back to the thread that sent the work
ok 4 - REQ-MSG-1: the chief of staff's reply comes back to the thread that sent the work
---
duration_ms: 593.922455
duration_ms: 616.013932
type: 'test'
...
# Subtest: REQ-MSG-1: a reply can't carry one thread instance's thread to another thread instance
ok 5 - REQ-MSG-1: a reply can't carry one thread instance's thread to another thread instance
---
duration_ms: 24.857971
duration_ms: 22.785202
type: 'test'
...
# Subtest: REQ-THREAD-1 REQ-USER-2: one thread's messages never reach another thread's holder
ok 6 - REQ-THREAD-1 REQ-USER-2: one thread's messages never reach another thread's holder
---
duration_ms: 27.519976
duration_ms: 27.208648
type: 'test'
...
# Subtest: REQ-LAUNCH-1: a message to a thread with no holder waits, and the next holder gets it
ok 7 - REQ-LAUNCH-1: a message to a thread with no holder waits, and the next holder gets it
---
duration_ms: 30.716822
duration_ms: 29.67741
type: 'test'
...
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1: threadIdle releases only a thread with nothing waiting, and only for its holder
ok 8 - REQ-THREAD-2 REQ-LAUNCH-1: threadIdle releases only a thread with nothing waiting, and only for its holder
---
duration_ms: 33.754906
duration_ms: 33.136315
type: 'test'
...
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1: a message delivered to a run that ended unread doesn't hold up the next holder
ok 9 - REQ-THREAD-2 REQ-LAUNCH-1: a message delivered to a run that ended unread doesn't hold up the next holder
---
duration_ms: 29.046481
duration_ms: 30.610794
type: 'test'
...
# Subtest: REQ-ROLE-2 REQ-THREAD-1 Q169: a role.revoke the human approved ends every thread run of the assistant
ok 10 - REQ-ROLE-2 REQ-THREAD-1 Q169: a role.revoke the human approved ends every thread run of the assistant
---
duration_ms: 26.449042
duration_ms: 27.293744
type: 'test'
...
# Subtest: Q169 REQ-USER-2: assistant.stop ends the human's own assistant thread runs, and only the human's
ok 11 - Q169 REQ-USER-2: assistant.stop ends the human's own assistant thread runs, and only the human's
---
duration_ms: 38.524966
duration_ms: 39.426851
type: 'test'
...
# Subtest: REQ-USER-2: the human verbs refuse another owner's thread
ok 12 - REQ-USER-2: the human verbs refuse another owner's thread
---
duration_ms: 28.558392
duration_ms: 30.185753
type: 'test'
...
# Subtest: REQ-THREAD-1: thread.create refuses when the business has no thread instance or more than one
ok 13 - REQ-THREAD-1: thread.create refuses when the business has no thread instance or more than one
---
duration_ms: 23.166467
duration_ms: 25.774336
type: 'test'
...
# Subtest: REQ-ORG-2: projects and threads are named once, and the repo names a business project
ok 14 - REQ-ORG-2: projects and threads are named once, and the repo names a business project
---
duration_ms: 28.154835
duration_ms: 26.886111
type: 'test'
...
# Subtest: REQ-THREAD-2: thread.messages returns the thread's history in pages and writes nothing
ok 15 - REQ-THREAD-2: thread.messages returns the thread's history in pages and writes nothing
---
duration_ms: 86.802213
duration_ms: 90.298865
type: 'test'
...
# Subtest: project.create refuses a repository name without its matching repo before any write
ok 16 - project.create refuses a repository name without its matching repo before any write
---
duration_ms: 15.244016
duration_ms: 16.900927
type: 'test'
...
# Subtest: project.create keeps unrelated names with and without a repository
ok 17 - project.create keeps unrelated names with and without a repository
---
duration_ms: 11.57841
duration_ms: 11.07789
type: 'test'
...
# Subtest: C2-09a: explicit creative instances bind independent threads, default sessions and holders
ok 18 - C2-09a: explicit creative instances bind independent threads, default sessions and holders
---
duration_ms: 46.82113
duration_ms: 47.924595
type: 'test'
...
# Subtest: C2-09a: explicit missing, non-thread and malformed selectors create no thread or session
ok 19 - C2-09a: explicit missing, non-thread and malformed selectors create no thread or session
---
duration_ms: 20.263528
duration_ms: 19.917458
type: 'test'
...
1..19
@@ -121,4 +121,4 @@ ok 19 - C2-09a: explicit missing, non-thread and malformed selectors create no t
# cancelled 0
# skipped 0
# todo 0
# duration_ms 1283.575562
# duration_ms 1316.555344
agents/rocko/work/queue-219/run-4a9c-mos1408/single-bus-user-principal.test.tap
+24 -24
View File
@@ -2,139 +2,139 @@ TAP version 13
# Subtest: R3: bindUser binds a granted user and refuses one with no live grant
ok 1 - R3: bindUser binds a granted user and refuses one with no live grant
---
duration_ms: 15.216913
duration_ms: 14.967712
type: 'test'
...
# Subtest: R3: a user named like the business human, the tester or a principal word is refused, whatever the grants say
ok 2 - R3: a user named like the business human, the tester or a principal word is refused, whatever the grants say
---
duration_ms: 10.127905
duration_ms: 10.570753
type: 'test'
...
# Subtest: R3: each collaborator verb is allowed to a granted user
ok 3 - R3: each collaborator verb is allowed to a granted user
---
duration_ms: 18.491408
duration_ms: 20.155376
type: 'test'
...
# Subtest: R3: every verb off the collaborator list refuses a user access-refused before its own checks
ok 4 - R3: every verb off the collaborator list refuses a user access-refused before its own checks
---
duration_ms: 95.840429
duration_ms: 102.151204
type: 'test'
...
# Subtest: R3: task, web and host verbs refuse a user access-refused
ok 5 - R3: task, web and host verbs refuse a user access-refused
---
duration_ms: 22.333602
duration_ms: 23.297818
type: 'test'
...
# Subtest: R3 leak: project.list shows granted projects only
ok 6 - R3 leak: project.list shows granted projects only
---
duration_ms: 12.494935
duration_ms: 13.028484
type: 'test'
...
# Subtest: R3 leak: thread.create needs the project and the thread instance granted, and an ungranted id reads as one that does not exist
ok 7 - R3 leak: thread.create needs the project and the thread instance granted, and an ungranted id reads as one that does not exist
---
duration_ms: 15.195921
duration_ms: 17.131417
type: 'test'
...
# Subtest: R3 leak: thread.list shows the user its own threads that are still granted, never others
ok 8 - R3 leak: thread.list shows the user its own threads that are still granted, never others
---
duration_ms: 33.037437
duration_ms: 34.619156
type: 'test'
...
# Subtest: R3 leak: names shows granted instances only
ok 9 - R3 leak: names shows granted instances only
---
duration_ms: 14.891286
duration_ms: 15.416042
type: 'test'
...
# Subtest: R3: thread.send is from user:<id> and writes no human.input
ok 10 - R3: thread.send is from user:<id> and writes no human.input
---
duration_ms: 13.366772
duration_ms: 13.82133
type: 'test'
...
# Subtest: R3: a reply-chain message.send into another user thread is refused
ok 11 - R3: a reply-chain message.send into another user thread is refused
---
duration_ms: 15.523733
duration_ms: 15.982484
type: 'test'
...
# Subtest: R3: the run reply to a user message reaches that user thread.messages, with no waiting and no notice
ok 12 - R3: the run reply to a user message reaches that user thread.messages, with no waiting and no notice
---
duration_ms: 18.163702
duration_ms: 19.055939
type: 'test'
...
# Subtest: R3: a reply to: user without a matching in_reply_to is refused user-reply-required
ok 13 - R3: a reply to: user without a matching in_reply_to is refused user-reply-required
---
duration_ms: 26.445744
duration_ms: 28.510227
type: 'test'
...
# Subtest: R3: a non-thread run, the human and the tester cannot send to: user
ok 14 - R3: a non-thread run, the human and the tester cannot send to: user
---
duration_ms: 17.29104
duration_ms: 18.072201
type: 'test'
...
# Subtest: R3: a user thread run cannot message the owner, while its uncited gated raise reaches only the owner inbox, B9
ok 15 - R3: a user thread run cannot message the owner, while its uncited gated raise reaches only the owner inbox, B9
---
duration_ms: 19.258704
duration_ms: 20.4668
type: 'test'
...
# Subtest: R3: a removed or expired grant refuses the next request access-revoked, and the file is read per request
ok 16 - R3: a removed or expired grant refuses the next request access-revoked, and the file is read per request
---
duration_ms: 18.231409
duration_ms: 17.954184
type: 'test'
...
# Subtest: R3: a user refusal is recorded as action.refused by user:<id>
ok 17 - R3: a user refusal is recorded as action.refused by user:<id>
---
duration_ms: 13.797301
duration_ms: 15.466589
type: 'test'
...
# Subtest: R3: a business with a role keyed user refuses invalid-business
ok 18 - R3: a business with a role keyed user refuses invalid-business
---
duration_ms: 9.468564
duration_ms: 10.080838
type: 'test'
...
# Subtest: R3: name.set refuses the name user
ok 19 - R3: name.set refuses the name user
---
duration_ms: 9.752458
duration_ms: 10.585336
type: 'test'
...
# Subtest: R3 r4: while halted, a granted user's thread.send refuses processing-halted and thread.messages still answers
ok 20 - R3 r4: while halted, a granted user's thread.send refuses processing-halted and thread.messages still answers
---
duration_ms: 13.617784
duration_ms: 14.198383
type: 'test'
...
# Subtest: R3 r4: the chief's hire refuses an instance named user with the code it gives human and tester
ok 21 - R3 r4: the chief's hire refuses an instance named user with the code it gives human and tester
---
duration_ms: 14.726171
duration_ms: 16.565998
type: 'test'
...
# Subtest: R3 r4: a non-function access throws before the store is read
ok 22 - R3 r4: a non-function access throws before the store is read
---
duration_ms: 0.105564
duration_ms: 0.139037
type: 'test'
...
# Subtest: C2-09a: naming an instance cannot bypass its collaborator grant or disclose an ungranted project
ok 23 - C2-09a: naming an instance cannot bypass its collaborator grant or disclose an ungranted project
---
duration_ms: 15.883063
duration_ms: 17.431688
type: 'test'
...
1..23
@@ -145,4 +145,4 @@ ok 23 - C2-09a: naming an instance cannot bypass its collaborator grant or discl
# cancelled 0
# skipped 0
# todo 0
# duration_ms 523.149354
# duration_ms 550.515661
agents/rocko/work/queue-219/run-4a9c-mos1408/single-cli-launcher.test.tap
+52 -81
View File
@@ -2,102 +2,102 @@ TAP version 13
# Subtest: C2-04: launcher workspace clones code but never the library
ok 1 - C2-04: launcher workspace clones code but never the library
---
duration_ms: 1444.885132
duration_ms: 1386.548788
type: 'test'
...
# Subtest: bus start --pm: the launcher instance (the chief of staff) runs under its own PID namespace, registered, with a manifest
ok 2 - bus start --pm: the launcher instance (the chief of staff) runs under its own PID namespace, registered, with a manifest
---
duration_ms: 1312.408111
duration_ms: 1321.365393
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r910aab09c0d6","instance":"chief","turn":"368e3045-8783-47d3-8ae1-e429b321d9b1","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r5bb5f0657d94","instance":"coder","turn":"3432d01f-ca94-4a5e-88d3-19588a40a81d","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"rfeb27e280740","instance":"chief","turn":"6c7140a2-fbf2-4eb5-aade-18915e5d6071","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r4d1379ff54ed","instance":"coder","turn":"0828e9f0-3389-4d81-b773-d33ac8ed9436","source":"@none","code":"baseline-unknown"}
# Subtest: the chief of staff launches a coder through its launch tool; the coder answers; refusals name their code
ok 3 - the chief of staff launches a coder through its launch tool; the coder answers; refusals name their code
---
duration_ms: 745.868459
duration_ms: 729.440258
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"3bd3e4d7-3af4-4a1c-99f1-a8f25b7ab1dd","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"b2db478d-2905-49fd-a81a-0800643bed6a","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"ac2aa380-f3a0-40d4-960f-a543acb8c431","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"e8b5124b-591b-4d5b-829c-e944bb3e24bb","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"6a6e1fa4-5182-42dc-bbc2-26f136eedee3","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"54eb77b5-3880-4afb-9772-0b9d590eb328","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"re94397bc3680","instance":"pm","turn":"11fe8b92-1dae-416a-838b-ae305db74bc6","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0f3692812967","instance":"chief","turn":"68266357-b477-433c-99ed-f1af37143d91","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r6b4b3482e67f","instance":"chief","turn":"aa4f1c16-5525-464e-bf32-86dce3279b86","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r1c029998bdea","instance":"pm","turn":"9bcd06eb-6a90-41fb-80ae-56a32bc1c628","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r6b4b3482e67f","instance":"chief","turn":"8bbc58a8-f1e1-478c-957b-76e1d7d3a0d4","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r1c029998bdea","instance":"pm","turn":"e1f9e391-0762-4643-bdfb-737a3f75468c","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r1c029998bdea","instance":"pm","turn":"ee01381b-77c5-4737-9963-cc39bfcf3329","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r6b4b3482e67f","instance":"chief","turn":"48edb0d5-0ec4-4e59-9eae-4f767252eaf9","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r1c029998bdea","instance":"pm","turn":"837ddcc0-6e74-408d-a21f-aeefc287e380","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r6b4b3482e67f","instance":"chief","turn":"702b0c7b-18c4-4f01-b71b-29fdf5ae1d79","source":"@none","code":"baseline-unknown"}
# Subtest: a launched pm's request_staff reaches the chief of staff; no other session has the tool and the launch limits still hold
ok 4 - a launched pm's request_staff reaches the chief of staff; no other session has the tool and the launch limits still hold
---
duration_ms: 1245.265675
duration_ms: 1260.785468
type: 'test'
...
# Subtest: each launch makes sure the workspace has a clone of the project: cloned, fast-forwarded, or fetched and logged
ok 5 - each launch makes sure the workspace has a clone of the project: cloned, fast-forwarded, or fetched and logged
---
duration_ms: 4072.119958
duration_ms: 4079.777924
type: 'test'
...
# Subtest: a role the broker says holds a merge decision gets land_work, its prompt line, its landing and the git socket; without it, none
ok 6 - a role the broker says holds a merge decision gets land_work, its prompt line, its landing and the git socket; without it, none
---
duration_ms: 621.888037
duration_ms: 602.445534
type: 'test'
...
# Subtest: REQ-LAUNCH-1 the tick starts a listed merge decision holder once, with land_work, the Landing line and its landing turn; an unlisted holder starts nothing
ok 7 - REQ-LAUNCH-1 the tick starts a listed merge decision holder once, with land_work, the Landing line and its landing turn; an unlisted holder starts nothing
---
duration_ms: 417.133166
duration_ms: 401.42897
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r8e91dd37dc4b","instance":"coder","turn":"a7b24e30-ac5e-47cf-a951-90cf0d948b4d","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r91e3ad863ad3","instance":"coder","turn":"b80d99c8-e809-4461-9c46-6b36ca47b775","source":"@none","code":"baseline-unknown"}
# Subtest: a holder running since before the resolution is stopped once the broker releases it, land-relaunch, and the next tick starts it: landing turn first, then the message that waited
ok 8 - a holder running since before the resolution is stopped once the broker releases it, land-relaunch, and the next tick starts it: landing turn first, then the message that waited
---
duration_ms: 730.904044
duration_ms: 676.724798
type: 'test'
...
# Subtest: a landing run that ended isn't started again for its decision, a spent decision starts nothing, and a new decision starts the holder
ok 9 - a landing run that ended isn't started again for its decision, a spent decision starts nothing, and a new decision starts the holder
---
duration_ms: 698.470719
duration_ms: 578.985078
type: 'test'
...
# Subtest: after a restart, the new host's first tick starts a holder whose decision is still held
ok 10 - after a restart, the new host's first tick starts a holder whose decision is still held
---
duration_ms: 920.432738
duration_ms: 870.835521
type: 'test'
...
# Subtest: a refused landing start is logged once per code with its decision, isn't a start, and the next tick with room starts the holder
ok 11 - a refused landing start is logged once per code with its decision, isn't a start, and the next tick with room starts the holder
---
duration_ms: 641.309798
duration_ms: 633.801547
type: 'test'
...
# Subtest: a project clone that can't be made refuses checkout-failed, from --chief and from a session, with no run and no clone left
ok 12 - a project clone that can't be made refuses checkout-failed, from --chief and from a session, with no run and no clone left
---
duration_ms: 267.647539
duration_ms: 281.44642
type: 'test'
...
# Subtest: a runner that stops at once ends its launch with the runner's reason
ok 13 - a runner that stops at once ends its launch with the runner's reason
---
duration_ms: 332.423482
duration_ms: 350.182818
type: 'test'
...
# Subtest: a Claude Code launch with no session credential refuses before it starts
ok 14 - a Claude Code launch with no session credential refuses before it starts
---
duration_ms: 181.931254
duration_ms: 227.256782
type: 'test'
...
# Subtest: a pi launch needs no session credential: pi logs in through its own ENV_ALLOW variables
ok 15 - a pi launch needs no session credential: pi logs in through its own ENV_ALLOW variables
---
duration_ms: 315.27683
duration_ms: 355.020473
type: 'test'
...
# usage: {"event":"plugin-refused","kind":"harness","name":"down","code":"missing","message":"/mnt/storage/scratch/rocko-r219/packages/plugins/harness/down is missing","kept":[]}
@@ -105,155 +105,126 @@ ok 15 - a pi launch needs no session credential: pi logs in through its own ENV_
# Subtest: row 65 a failed primary preflight launches the fallback on a fixture harness module, recording the route and the reason
ok 16 - row 65 a failed primary preflight launches the fallback on a fixture harness module, recording the route and the reason
---
duration_ms: 353.028786
duration_ms: 395.228029
type: 'test'
...
# Subtest: a runner killed from the host ends its launch as killed, not failed
ok 17 - a runner killed from the host ends its launch as killed, not failed
---
duration_ms: 375.548364
duration_ms: 426.266157
type: 'test'
...
# Subtest: a missing or failing bwrap refuses sandbox-unavailable before anything starts; there is no unconfined fallback
ok 18 - a missing or failing bwrap refuses sandbox-unavailable before anything starts; there is no unconfined fallback
---
duration_ms: 187.871873
duration_ms: 224.638023
type: 'test'
...
# Subtest: row 64 a role skill that isn't enabled refuses skill-not-enabled, and one that isn't a plain directory skill-refused, before anything starts
ok 19 - row 64 a role skill that isn't enabled refuses skill-not-enabled, and one that isn't a plain directory skill-refused, before anything starts
---
duration_ms: 187.807189
duration_ms: 193.63499
type: 'test'
...
# Subtest: row 213 a creative instance's persona is read from <configDir>/personas: off its digest the launch fails with the mismatch as its reason
not ok 20 - row 213 a creative instance's persona is read from <configDir>/personas: off its digest the launch fails with the mismatch as its reason
ok 20 - row 213 a creative instance's persona is read from <configDir>/personas: off its digest the launch fails with the mismatch as its reason
---
duration_ms: 255.698016
duration_ms: 276.964378
type: 'test'
location: '/mnt/storage/scratch/rocko-r219/packages/cli/tests/launcher.test.mjs:766:1'
failureType: 'testCodeFailure'
error: |-
Expected values to be strictly deep-equal:
+ actual - expected
[
+ 'compactions',
+ undefined,
+ 2
- 'refused',
- 'launch-failed',
- 1
]
code: 'ERR_ASSERTION'
name: 'AssertionError'
expected:
0: 'refused'
1: 'launch-failed'
2: 1
actual:
0: 'compactions'
2: 2
operator: 'deepStrictEqual'
stack: |-
TestContext.<anonymous> (file:///mnt/storage/scratch/rocko-r219/packages/cli/tests/launcher.test.mjs:789:10)
process.processTicksAndRejections (node:internal/process/task_queues:104:5)
async Test.run (node:internal/test_runner/test:1409:7)
async Test.processPendingSubtests (node:internal/test_runner/test:974:7)
...
# Subtest: row 64 on Claude Code a role skill that isn't enabled refuses the same way, before anything starts
ok 21 - row 64 on Claude Code a role skill that isn't enabled refuses the same way, before anything starts
---
duration_ms: 194.030218
duration_ms: 199.95263
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r3715d40bd7fb","instance":"chief","turn":"4c85d22f-fdab-4ab7-ad8a-6b4c4d1fbf72","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r16ae936abadf","instance":"coder","turn":"2c6b06f1-8f36-4261-81b7-2689b9bb7ff4","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0292ea4215c0","instance":"chief","turn":"e2a42abe-43ec-4873-a349-c93850a0b2d1","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r0292ea4215c0","instance":"chief","turn":"b84fdcd2-08f1-4c7d-a1be-edf183ecf035","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"rb645b3bdbf17","instance":"coder","turn":"8c651e69-aef3-428e-9ecb-fa2c53e86f79","source":"@none","code":"baseline-unknown"}
# Subtest: a real Claude Code coder's shell can't read a stand-in secret or anything else its sandbox doesn't hold
ok 22 - a real Claude Code coder's shell can't read a stand-in secret or anything else its sandbox doesn't hold
---
duration_ms: 1456.773218
duration_ms: 1419.59525
type: 'test'
...
# Subtest: a host that died hard leaves its sessions to the next host, which kills them and ends their runs so the role can be launched again
ok 23 - a host that died hard leaves its sessions to the next host, which kills them and ends their runs so the role can be launched again
---
duration_ms: 1063.59923
duration_ms: 1046.224325
type: 'test'
...
# Subtest: a host that died hard leaves its sessions to the next host, which finds one already exited (23) and ends their runs so the role can be launched again
ok 24 - a host that died hard leaves its sessions to the next host, which finds one already exited (23) and ends their runs so the role can be launched again
---
duration_ms: 4016.888246
duration_ms: 3988.178511
type: 'test'
...
# Subtest: bus start --no-launch leaves an earlier host's live session alone: no signal, no end, sessions.json as it was
ok 25 - bus start --no-launch leaves an earlier host's live session alone: no signal, no end, sessions.json as it was
---
duration_ms: 237.364574
duration_ms: 242.392974
type: 'test'
...
# Subtest: bus start --no-launch refuses every launch: the PM launch and a session's request, each logged, nothing spawned
ok 26 - bus start --no-launch refuses every launch: the PM launch and a session's request, each logged, nothing spawned
---
duration_ms: 197.775267
duration_ms: 218.198607
type: 'test'
...
# Subtest: bus start --no-launch starts no thread tick; the same host with launches runs it
ok 27 - bus start --no-launch starts no thread tick; the same host with launches runs it
---
duration_ms: 1181.987654
duration_ms: 1199.857353
type: 'test'
...
# Subtest: a malformed sessions.json refuses the host start with exit 3 and stays as it was
ok 28 - a malformed sessions.json refuses the host start with exit 3 and stays as it was
---
duration_ms: 177.111363
duration_ms: 181.02391
type: 'test'
...
# Subtest: an over-long launch request is refused at once, not at the 10 s idle timeout
ok 29 - an over-long launch request is refused at once, not at the 10 s idle timeout
---
duration_ms: 183.364128
duration_ms: 181.674266
type: 'test'
...
# Subtest: a launch client that never closes its side doesn't hold the host's close
ok 30 - a launch client that never closes its side doesn't hold the host's close
---
duration_ms: 179.49662
duration_ms: 183.632625
type: 'test'
...
# Subtest: a runner that ignores SIGTERM is killed when the host closes
ok 31 - a runner that ignores SIGTERM is killed when the host closes
---
duration_ms: 1352.083242
duration_ms: 1365.88402
type: 'test'
...
# Subtest: kill switch refuses chief and hire before launch work and a clear permits a later request
ok 32 - kill switch refuses chief and hire before launch work and a clear permits a later request
---
duration_ms: 319.505559
duration_ms: 334.261623
type: 'test'
...
# Subtest: kill switch stops an actual managed namespace and records the halt reason without rewriting its bundle
ok 33 - kill switch stops an actual managed namespace and records the halt reason without rewriting its bundle
---
duration_ms: 334.076309
duration_ms: 337.104395
type: 'test'
...
# Subtest: a launch waiting across halt and resume cannot use its stale admission
ok 34 - a launch waiting across halt and resume cannot use its stale admission
---
duration_ms: 201.932098
duration_ms: 194.683714
type: 'test'
...
1..34
# tests 34
# suites 0
# pass 33
# fail 1
# pass 34
# fail 0
# cancelled 0
# skipped 0
# todo 0
# duration_ms 26522.233904
# duration_ms 26492.10694
agents/rocko/work/queue-219/run-4a9c-mos1408/single-cli-thread-launch.test.tap
+122
View File
@@ -0,0 +1,122 @@
TAP version 13
# usage: {"event":"usage-unknown","business":"acme","run":"r2204f4cc976c","instance":"assistant","turn":"fdd36b75-12af-4495-ba60-8a2fdd991676","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r42619c482fdd","instance":"assistant","turn":"4a493440-df70-4de2-a9be-f31bb9efbe67","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r65dae8bd493b","instance":"assistant","turn":"2a27c708-e430-4bcc-82b5-67dc51173d46","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r4f264ceb0a50","instance":"assistant","turn":"dedfd89c-7a7a-4bb8-ba67-ca0e6a417ee8","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it
ok 1 - REQ-THREAD-2 REQ-LAUNCH-1 REQ-MSG-1 a thread message starts the thread's session, which stops when idle; its history survives the stop and a restart and no other thread sees it
---
duration_ms: 5837.256276
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"red085121d9a7","instance":"assistant","turn":"536c8b62-f126-4b17-a1f2-756e2aede65e","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"ree31908db53d","instance":"assistant","turn":"f23f7966-9c87-4d7b-9d9a-93211c1431c0","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't
ok 2 - REQ-THREAD-2 REQ-LAUNCH-1 a running thread counts against its model's limit and an idle-stopped one doesn't
---
duration_ms: 1713.759995
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r5c82fe368237","instance":"assistant","turn":"081a280e-73b4-48fc-89a9-688e73704186","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a turn longer than the idle time isn't stopped, and the thread idles out after it
ok 3 - REQ-THREAD-2 REQ-LAUNCH-1 a turn longer than the idle time isn't stopped, and the thread idles out after it
---
duration_ms: 4442.41406
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r008070c44356","instance":"assistant","turn":"3175be8d-24d9-4d46-b9fe-e08c8edd0a5e","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r008070c44356","instance":"assistant","turn":"961030fd-2dd3-4deb-a9be-f10af56ba7f7","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a message sent after the idle snapshot keeps the session, which answers it
ok 4 - REQ-THREAD-2 REQ-LAUNCH-1 a message sent after the idle snapshot keeps the session, which answers it
---
duration_ms: 2897.279317
type: 'test'
...
# Subtest: REQ-ROLE-2 REQ-LAUNCH-1 a thread held by a run the launcher didn't start gets no second session
ok 5 - REQ-ROLE-2 REQ-LAUNCH-1 a thread held by a run the launcher didn't start gets no second session
---
duration_ms: 79.744891
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"rf65e96bfb0f4","instance":"assistant","turn":"61a6ab74-b6bd-4274-a83e-0f8fb4f61a68","source":"@none","code":"baseline-unknown"}
# Subtest: REQ-LAUNCH-1 a thread run's session file has no landing, even when landHolders names its instance
ok 6 - REQ-LAUNCH-1 a thread run's session file has no landing, even when landHolders names its instance
---
duration_ms: 374.600592
type: 'test'
...
# Subtest: REQ-LAUNCH-1 a run that ends without taking its thread's message isn't started again for that message
ok 7 - REQ-LAUNCH-1 a run that ends without taking its thread's message isn't started again for that message
---
duration_ms: 232.164242
type: 'test'
...
# Subtest: REQ-THREAD-2 REQ-LAUNCH-1 a thread id that isn't a safe segment, or a thread of a non-thread instance, launches nothing
ok 8 - REQ-THREAD-2 REQ-LAUNCH-1 a thread id that isn't a safe segment, or a thread of a non-thread instance, launches nothing
---
duration_ms: 226.367358
type: 'test'
...
# Subtest: REQ-THREAD-1 REQ-LAUNCH-1 the chief can't launch the assistant outside a thread
ok 9 - REQ-THREAD-1 REQ-LAUNCH-1 the chief can't launch the assistant outside a thread
---
duration_ms: 78.315815
type: 'test'
...
# Subtest: C2-09a: fromSession refuses a creative instance outside a thread without a sandbox
ok 10 - C2-09a: fromSession refuses a creative instance outside a thread without a sandbox
---
duration_ms: 74.784926
type: 'test'
...
# limits: {"event":"limit-reached","business":"acme","check":"token-limit","export":"mayLaunch","subject":{"instance":"assistant","provider":"zai","model":"claude-sonnet-5-5","account":null},"path":["tokens","instances","assistant"],"limit":0,"count":0,"unknownTurns":0}
# limits: {"event":"limit-reached","business":"acme","check":"token-limit","export":"mayLaunch","subject":{"instance":"assistant","provider":"zai","model":"claude-sonnet-5-5","account":null},"path":["tokens","instances","assistant"],"limit":0,"count":0,"unknownTurns":0}
# Subtest: REQ-LIMIT-3 REQ-LIMIT-4 a thread start whose instance is at its token limit is refused, logged once with the limit and the count
ok 11 - REQ-LIMIT-3 REQ-LIMIT-4 a thread start whose instance is at its token limit is refused, logged once with the limit and the count
---
duration_ms: 192.227024
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r3ffa99981f81","instance":"assistant","turn":"c194605d-1b92-488c-9afe-2599f205e80e","source":"@none","code":"baseline-unknown"}
# limits: {"event":"limit-reached","business":"acme","check":"token-limit","export":"mustStop","subject":{"instance":"assistant","provider":"zai","model":"claude-sonnet-5-5","account":null},"path":["tokens","instances","assistant"],"limit":0,"count":0,"unknownTurns":1}
# Subtest: REQ-LIMIT-4 a thread run at its token limit stops at the end of its turn: the reply lands, and the end record names the limit
ok 12 - REQ-LIMIT-4 a thread run at its token limit stops at the end of its turn: the reply lands, and the end record names the limit
---
duration_ms: 346.819478
type: 'test'
...
# usage: {"event":"usage-unknown","business":"acme","run":"r013acfa3de9d","instance":"bean","turn":"26896136-02b5-4948-8c84-7e0be580c485","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r13746c56cf7b","instance":"chet","turn":"2a7d4bed-79e7-4b74-b602-c07fe90be87f","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"r013acfa3de9d","instance":"bean","turn":"32222fad-092d-4ac9-b5de-d40de519bf82","source":"@none","code":"baseline-unknown"}
# Subtest: C2-09a: creative thread messages start distinct runs and keep each instance history separate
not ok 13 - C2-09a: creative thread messages start distinct runs and keep each instance history separate
---
duration_ms: 746.425172
type: 'test'
location: '/mnt/storage/scratch/rocko-r219/packages/cli/tests/thread-launch.test.mjs:463:1'
failureType: 'testCodeFailure'
error: "ENOENT: no such file or directory, open '/mnt/storage/scratch/tmp/rbyz9a6iu/mosaic-thread-Cgx1tR/data/threads/acme/0a27cae9-cdb8-436d-8cc8-a59b316577e9/session/history'"
code: 'ENOENT'
stack: |-
readFileSync (node:fs:621:20)
TestContext.<anonymous> (file:///mnt/storage/scratch/rocko-r219/packages/cli/tests/thread-launch.test.mjs:489:16)
async Test.run (node:internal/test_runner/test:1409:7)
async Test.processPendingSubtests (node:internal/test_runner/test:974:7)
...
# usage: {"event":"usage-unknown","business":"acme","run":"rb9998f7e5721","instance":"bean","turn":"6c83f086-940d-43ab-8219-0ee1b9dd4c7d","source":"@none","code":"baseline-unknown"}
# usage: {"event":"usage-unknown","business":"acme","run":"rdf0bd4d3e49a","instance":"bean","turn":"663ed95c-c09b-4053-aeb7-1696b6acf272","source":"@none","code":"baseline-unknown"}
# Subtest: C2-09a: terminating one creative thread does not signal an unselected peer of the same instance
ok 14 - C2-09a: terminating one creative thread does not signal an unselected peer of the same instance
---
duration_ms: 643.667218
type: 'test'
...
1..14
# tests 14
# suites 0
# pass 13
# fail 1
# cancelled 0
# skipped 0
# todo 0
# duration_ms 18010.958178
packages/cli/tests/thread-launch.test.mjs
+4 -2
View File
@@ -486,8 +486,10 @@ test('C2-09a: creative thread messages start distinct runs and keep each instanc
assert.deepEqual((await send(bean, 'bean', 'Bean input')).before, []);
assert.deepEqual((await send(chet, 'chet', 'Chet input')).before, []);
assert.deepEqual((await send(bean, 'bean', 'Bean again')).before, ['Bean input']);
assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', bean, 'session', 'history'), 'utf8'), 'Bean input\nBean again\n');
assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', chet, 'session', 'history'), 'utf8'), 'Chet input\n');
assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', bean, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === bean).session, 'session', 'history'), 'utf8'), 'Bean input\nBean again\n');
assert.equal(readFileSync(join(f.dataRoot, 'threads', 'acme', chet, 'sessions', host.runtime.threadsState('acme').find(x => x.thread === chet).session, 'session', 'history'), 'utf8'), 'Chet input\n');
assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', bean, 'session')), false);
assert.equal(existsSync(join(f.dataRoot, 'threads', 'acme', chet, 'session')), false);
const launches = launchLog(f).filter(row => row.event === 'launch');
assert.ok(launches.some(row => row.instance === 'bean' && row.thread === bean));
assert.ok(launches.some(row => row.instance === 'chet' && row.thread === chet));