agents-relay 2.0.228 → 2.0.230
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +16 -2
- package/agents/chatgpt-worker.agent.md +1 -1
- package/dist/cli-context.js +1 -0
- package/dist/cli-escalation.js +64 -19
- package/dist/cli-help.js +4 -4
- package/dist/interactive-request.js +7 -2
- package/dist/relayd-control.js +3 -4
- package/package.json +1 -1
- package/skills/agents-relay/SKILL.md +25 -1
- package/skills/agents-relay/contracts/task-recovery-flows.md +10 -0
package/README.md
CHANGED
|
@@ -9,6 +9,20 @@ The canonical V2 architecture contract is
|
|
|
9
9
|
[DESIGN-PRINCIPLES.md](DESIGN-PRINCIPLES.md). README sections below describe
|
|
10
10
|
the runtime; they do not replace that contract.
|
|
11
11
|
|
|
12
|
+
**Escalation executor:** `AGENTS_RELAY_ESCALATION_COMMAND` selects an external
|
|
13
|
+
executable (absolute path) or a JSON argv array with a fixed command prefix.
|
|
14
|
+
For example, the Neo deployment uses
|
|
15
|
+
`AGENTS_RELAY_ESCALATION_COMMAND='["/opt/homebrew/bin/neo","escalation"]'`.
|
|
16
|
+
Relay appends `--handoff-file`, optional `--on-needs-user-file`, and `--cwd`
|
|
17
|
+
without using a shell. No Neo executable is assumed. Missing/failed executors
|
|
18
|
+
produce `technical_failure` rather than silently resolving a blocker.
|
|
19
|
+
|
|
20
|
+
**Interactive Review:** Relay owns the generic
|
|
21
|
+
`review.interactive.begin/wait/ready/fail/abort` lifecycle, immutable revision
|
|
22
|
+
binding and decision correlation. The caller (e.g. Neo's Markcut MCP wrapper)
|
|
23
|
+
owns preview generation, media, UI and notifications. New waiting events use
|
|
24
|
+
`component: interactive-review`; existing recorded events retain their history.
|
|
25
|
+
|
|
12
26
|
**Harness/Project integration:** The intended Relay boundary is standalone and
|
|
13
27
|
provider-neutral: callers supply shared Agent/Skill capability sources and a
|
|
14
28
|
Job Execution Context, not a Neo installation. The [Harness-independence
|
|
@@ -294,8 +308,8 @@ flowchart LR
|
|
|
294
308
|
Failed[Failed task] --> Troubleshooter
|
|
295
309
|
Troubleshooter -->|technical| Repair[Repair / retry]
|
|
296
310
|
Troubleshooter -->|suspected human blocker| Escalation[Escalation graph]
|
|
297
|
-
Escalation --> Invoke[
|
|
298
|
-
Invoke -->
|
|
311
|
+
Escalation --> Invoke[Configured Escalation Executor]
|
|
312
|
+
Invoke --> Provider[External Provider, e.g. Neo]
|
|
299
313
|
Codex -->|resolved| Resume[Resume recovery]
|
|
300
314
|
Codex -->|failed| Technical[Technical recovery evidence]
|
|
301
315
|
Codex -->|needs_user| User[Notify user + task.blocked]
|
|
@@ -12,7 +12,7 @@ You execute one complete Relay task by submitting it to a fresh, regular ChatGPT
|
|
|
12
12
|
|
|
13
13
|
- Browser Workspace `platforms/chatgpt` is the sole owner of ChatGPT selectors, readiness checks, new-thread mechanics and submit verification.
|
|
14
14
|
- Relay owns worker lifecycle, task/event barriers, routing, and cancellation; Browser Workspace owns the one-shot auto-session lifecycle.
|
|
15
|
-
- Execute one new worker submission with `platform run chatgpt new-thread --session-id SESSION_ID`. Existing-thread delivery uses `new-turn`. Never use Temporary Chat for workers
|
|
15
|
+
- Execute one new worker submission with `platform run chatgpt new-thread --session-id SESSION_ID`. Existing-thread delivery uses `new-turn`. Never use Temporary Chat for workers requiring any configured MCP provider or durable execution context.
|
|
16
16
|
- Relay creates and stops a caller-owned WebHelm Session for each delivery. New worker conversations persist in ChatGPT history; do not reuse a pre-existing user tab.
|
|
17
17
|
- Preserve the account's current default model/thinking settings.
|
|
18
18
|
- A submission is accepted only after Browser Workspace returns a verified submit receipt.
|
package/dist/cli-context.js
CHANGED
|
@@ -14,6 +14,7 @@ export async function runContextCommand(action, args) {
|
|
|
14
14
|
const context = await resolveExecutionContext(projectPath, roleValue, {
|
|
15
15
|
workspaceRoot: arg(args, '--workspace-root') || undefined,
|
|
16
16
|
globalRoot: arg(args, '--global-root') || undefined,
|
|
17
|
+
sharedRoot: arg(args, '--shared-root') || undefined,
|
|
17
18
|
explicitSkills: arg(args, '--skills').split(',').filter(Boolean),
|
|
18
19
|
explicitAgents: arg(args, '--agents').split(',').filter(Boolean),
|
|
19
20
|
});
|
package/dist/cli-escalation.js
CHANGED
|
@@ -1,12 +1,32 @@
|
|
|
1
1
|
import { mkdtemp, rm, writeFile } from 'node:fs/promises';
|
|
2
2
|
import { tmpdir } from 'node:os';
|
|
3
|
-
import { join } from 'node:path';
|
|
3
|
+
import { isAbsolute, join } from 'node:path';
|
|
4
4
|
import { textOption, arg } from './cli-support.js';
|
|
5
5
|
import { runEscalationGraph } from './workflow/escalation.js';
|
|
6
|
-
import { spawnOwnedProcess } from './owned-process.js';
|
|
7
|
-
|
|
6
|
+
import { spawnOwnedProcess, terminateOwnedProcess } from './owned-process.js';
|
|
7
|
+
/** A caller-selected argv vector. Only the trusted operator supplies this
|
|
8
|
+
* environment value; task input is never parsed as a shell command. */
|
|
9
|
+
export function escalationCommand(env = process.env) {
|
|
10
|
+
const raw = env.AGENTS_RELAY_ESCALATION_COMMAND?.trim();
|
|
11
|
+
if (!raw)
|
|
12
|
+
return null;
|
|
13
|
+
let parsed;
|
|
14
|
+
try {
|
|
15
|
+
parsed = raw.startsWith('[') ? JSON.parse(raw) : [raw];
|
|
16
|
+
}
|
|
17
|
+
catch {
|
|
18
|
+
throw new Error('AGENTS_RELAY_ESCALATION_COMMAND must be an absolute executable or JSON argv array');
|
|
19
|
+
}
|
|
20
|
+
if (!Array.isArray(parsed) || parsed.length === 0 || parsed.length > 12 ||
|
|
21
|
+
!parsed.every(x => typeof x === 'string' && x.length > 0 && x.length <= 4096 && !/[\r\n\0]/.test(x)) ||
|
|
22
|
+
!isAbsolute(parsed[0]))
|
|
23
|
+
throw new Error('AGENTS_RELAY_ESCALATION_COMMAND must be an absolute executable or JSON argv array');
|
|
24
|
+
return { executable: parsed[0], prefixArgs: parsed.slice(1) };
|
|
25
|
+
}
|
|
26
|
+
/** Generic executor contract. No Neo-specific subcommand is assumed. */
|
|
27
|
+
export function escalationExecutorArgs(handoffPath, policyPath, cwd) {
|
|
8
28
|
return [
|
|
9
|
-
'
|
|
29
|
+
'--handoff-file', handoffPath,
|
|
10
30
|
...(policyPath ? ['--on-needs-user-file', policyPath] : []),
|
|
11
31
|
...(cwd ? ['--cwd', cwd] : []),
|
|
12
32
|
];
|
|
@@ -19,7 +39,17 @@ function handoffText(request) {
|
|
|
19
39
|
'',
|
|
20
40
|
].join('\n');
|
|
21
41
|
}
|
|
22
|
-
|
|
42
|
+
const failed = (summary) => ({ status: 'failed', summary, reason: summary });
|
|
43
|
+
export async function runConfiguredEscalation(request, env = process.env) {
|
|
44
|
+
let selected;
|
|
45
|
+
try {
|
|
46
|
+
selected = escalationCommand(env);
|
|
47
|
+
}
|
|
48
|
+
catch (error) {
|
|
49
|
+
return failed(error instanceof Error ? error.message : String(error));
|
|
50
|
+
}
|
|
51
|
+
if (!selected)
|
|
52
|
+
return failed('Escalation executor not configured: set AGENTS_RELAY_ESCALATION_COMMAND');
|
|
23
53
|
const tempRoot = await mkdtemp(join(tmpdir(), 'agents-relay-escalation-'));
|
|
24
54
|
try {
|
|
25
55
|
const handoffPath = join(tempRoot, 'handoff.md');
|
|
@@ -29,27 +59,42 @@ export async function runNeoEscalation(request) {
|
|
|
29
59
|
policyPath = join(tempRoot, 'on-needs-user.md');
|
|
30
60
|
await writeFile(policyPath, request.onNeedsUser, { encoding: 'utf8', mode: 0o600 });
|
|
31
61
|
}
|
|
32
|
-
const
|
|
33
|
-
return await new Promise(
|
|
34
|
-
const child = spawnOwnedProcess('neo', args, { invocation: 'escalation.neo', spawn: { cwd: request.cwd ?? process.cwd(), stdio: ['ignore', 'pipe', 'pipe'] } });
|
|
62
|
+
const argv = [...selected.prefixArgs, ...escalationExecutorArgs(handoffPath, policyPath, request.cwd)];
|
|
63
|
+
return await new Promise(resolve => {
|
|
35
64
|
let stdout = '';
|
|
36
|
-
let
|
|
37
|
-
child
|
|
38
|
-
|
|
39
|
-
|
|
65
|
+
let exceeded = false;
|
|
66
|
+
const child = spawnOwnedProcess(selected.executable, argv, {
|
|
67
|
+
invocation: 'escalation.configured',
|
|
68
|
+
timeoutMs: 600_000,
|
|
69
|
+
spawn: { cwd: request.cwd ?? process.cwd(), stdio: ['ignore', 'pipe', 'pipe'] },
|
|
70
|
+
});
|
|
71
|
+
child.stdout?.setEncoding('utf8').on('data', (chunk) => {
|
|
72
|
+
if (stdout.length + chunk.length > 256_000) {
|
|
73
|
+
exceeded = true;
|
|
74
|
+
void terminateOwnedProcess(child, 'abort');
|
|
75
|
+
}
|
|
76
|
+
else
|
|
77
|
+
stdout += chunk;
|
|
78
|
+
});
|
|
79
|
+
// Do not reflect stderr into the Job result: it can contain provider secrets.
|
|
80
|
+
child.stderr?.resume();
|
|
81
|
+
child.on('error', error => resolve(failed(`Escalation executor could not start: ${error.message}`)));
|
|
40
82
|
child.on('close', code => {
|
|
83
|
+
if (exceeded)
|
|
84
|
+
return resolve(failed('Escalation executor output exceeded limit'));
|
|
85
|
+
if (code !== 0)
|
|
86
|
+
return resolve(failed(`Escalation executor failed (exit ${code ?? 'signal'})`));
|
|
41
87
|
let parsed;
|
|
42
88
|
try {
|
|
43
89
|
parsed = JSON.parse(stdout.trim());
|
|
44
90
|
}
|
|
45
91
|
catch {
|
|
46
|
-
|
|
47
|
-
return;
|
|
48
|
-
}
|
|
49
|
-
if (!['resolved', 'failed', 'needs_user'].includes(parsed.status)) {
|
|
50
|
-
reject(new Error(`neo escalation returned invalid status ${String(parsed.status)}`));
|
|
51
|
-
return;
|
|
92
|
+
return resolve(failed('Escalation executor returned invalid JSON'));
|
|
52
93
|
}
|
|
94
|
+
if (!parsed || typeof parsed !== 'object' || !('status' in parsed) ||
|
|
95
|
+
!['resolved', 'failed', 'needs_user'].includes(String(parsed.status)) ||
|
|
96
|
+
!('summary' in parsed) || typeof parsed.summary !== 'string' || !parsed.summary.trim())
|
|
97
|
+
return resolve(failed('Escalation executor returned invalid result contract'));
|
|
53
98
|
resolve(parsed);
|
|
54
99
|
});
|
|
55
100
|
});
|
|
@@ -74,7 +119,7 @@ export async function runEscalationCommand(args) {
|
|
|
74
119
|
...(onNeedsUser.trim() ? { onNeedsUser } : {}),
|
|
75
120
|
...(arg(args, '--cwd') ? { cwd: arg(args, '--cwd') } : {}),
|
|
76
121
|
};
|
|
77
|
-
const outcome = await runEscalationGraph(request, { invoke:
|
|
122
|
+
const outcome = await runEscalationGraph(request, { invoke: runConfiguredEscalation });
|
|
78
123
|
console.log(JSON.stringify({ state: outcome.state, ...outcome.result }, null, 2));
|
|
79
124
|
if (outcome.state === 'technical_failure')
|
|
80
125
|
process.exitCode = 2;
|
package/dist/cli-help.js
CHANGED
|
@@ -19,7 +19,7 @@ Commands:
|
|
|
19
19
|
prompt Print raw Planner/Worker prompt from the production Builder
|
|
20
20
|
blocker add|resolve|show Manage cross-Job blocker dependencies
|
|
21
21
|
projection conflicts|resolve Inspect and repair deterministic GitHub projection conflicts
|
|
22
|
-
escalation Run the canonical escalation graph
|
|
22
|
+
escalation Run the canonical escalation graph with a configured external executor
|
|
23
23
|
context resolve Resolve shared project instructions, skills, agents, and runtimes
|
|
24
24
|
init Create a local demo job or initialize a GitHub job
|
|
25
25
|
record Backfill a completed task into durable history
|
|
@@ -59,7 +59,7 @@ Shortcut execution:
|
|
|
59
59
|
[--store-dir DIR] [--project-path DIR] [--shared-root DIR] [--concurrency 4]
|
|
60
60
|
|
|
61
61
|
The selected Task must have an Agent Graph. Project shortcuts at
|
|
62
|
-
agents/.shortcut/<agent>.agent.mjs override
|
|
62
|
+
agents/.shortcut/<agent>.agent.mjs override configured shared shortcuts. A Graph
|
|
63
63
|
with any missing shortcut falls back to the normal durable Worker before
|
|
64
64
|
executing any module; mixing shortcut and Worker nodes in one Graph is unsupported.
|
|
65
65
|
Shortcuts that fail before effects also return to the Worker queue. Nonhuman waits resume only from a matching SQLite Task receipt; EventBus
|
|
@@ -163,7 +163,7 @@ Required: --repo OWNER/REPO --id JOB_ID. Optional: --pr NUMBER. Running worker a
|
|
|
163
163
|
'job resume': `Resume a paused durable Job.
|
|
164
164
|
|
|
165
165
|
Required: --repo OWNER/REPO --id JOB_ID. Optional: --pr NUMBER. Interrupted work is requeued and normal reconciliation continues.`,
|
|
166
|
-
escalation: `Run the canonical escalation workflow for a suspected human/external blocker.\n\nRequired: --intent TEXT|--intent-file PATH and --blocked-on TEXT|--blocked-on-file PATH. Optional: --context/--context-file, --on-needs-user/--on-needs-user-file, --cwd. The
|
|
166
|
+
escalation: `Run the canonical escalation workflow for a suspected human/external blocker.\n\nRequired: --intent TEXT|--intent-file PATH and --blocked-on TEXT|--blocked-on-file PATH. Optional: --context/--context-file, --on-needs-user/--on-needs-user-file, --cwd. The workflow/escalation.mmd graph invokes an operator-configured executor and owns the resolved / failed / needs_user branches. Only needs_user selects the block-for-user path. Set AGENTS_RELAY_ESCALATION_COMMAND to an absolute executable path or JSON argv array (for example ["/opt/homebrew/bin/neo","escalation"]). No Neo executable is assumed by Relay; missing/broken executors produce technical_failure.`,
|
|
167
167
|
status: `Show live aggregate runtime status from the running Agents Relay service.
|
|
168
168
|
|
|
169
169
|
Usage:
|
|
@@ -274,7 +274,7 @@ Actions:
|
|
|
274
274
|
|
|
275
275
|
Required: --project-path PATH.
|
|
276
276
|
Common: --role orchestrator|planner|reviewer|worker|nested-worker, --skills a,b, --agents a,b.
|
|
277
|
-
Root overrides
|
|
277
|
+
Root overrides: --workspace-root PATH (or AGENTS_RELAY_WORKSPACE_ROOT), --global-root PATH, --shared-root PATH (or AGENTS_RELAY_SHARED_ROOT). Shared capabilities have no implicit Neo directory.
|
|
278
278
|
|
|
279
279
|
Example:
|
|
280
280
|
npx agents-relay context resolve --project-path ~/Workspace/agents-relay --role orchestrator`,
|
|
@@ -1,8 +1,13 @@
|
|
|
1
|
-
/** Relay-owned admission/ready/failure for
|
|
1
|
+
/** Relay-owned admission/ready/failure for host-owned interactive review requests. */
|
|
2
2
|
import { randomUUID } from 'node:crypto';
|
|
3
3
|
import { tryTransitionTaskEvent } from './task-transitions.js';
|
|
4
4
|
import { applyTaskUnblockRetrySnapshot } from './task-actions.js';
|
|
5
5
|
import { appendTaskComment } from './task-comments.js';
|
|
6
|
+
import { eventFor } from './events.js';
|
|
7
|
+
/** Host-neutral lifecycle event; the caller owns its preview/media/notification provider. */
|
|
8
|
+
export function interactiveWaitingEvent(jobId, taskId, parentTaskId, executionId) {
|
|
9
|
+
return eventFor(jobId, taskId, parentTaskId, 'task.interactive_waiting', 'waiting', 'Interactive review requested', 'orchestrator', {}, { id: `job/${jobId}/task/${taskId}/execution/${executionId}`, component: 'interactive-review' });
|
|
10
|
+
}
|
|
6
11
|
export function interactiveTemplate(jobId, taskId, executionId, invocationId) {
|
|
7
12
|
return { type: 'task.interactive_decision', source: `job/${jobId}/task/${taskId}/execution/${executionId}`,
|
|
8
13
|
data: { interactive: { jobId, taskId, executionId, invocationId } } };
|
|
@@ -92,7 +97,7 @@ export async function failInteractiveReview(store, jobId, taskId, executionId, i
|
|
|
92
97
|
task.interactiveInvocation = undefined;
|
|
93
98
|
task.error = null;
|
|
94
99
|
task.failureReason = undefined;
|
|
95
|
-
appendTaskComment(job, taskId, `
|
|
100
|
+
appendTaskComment(job, taskId, `Interactive review delivery failed; rerun review request: ${reason.slice(0, 500)}`);
|
|
96
101
|
task.updatedAt = new Date().toISOString();
|
|
97
102
|
requeued = true;
|
|
98
103
|
}
|
package/dist/relayd-control.js
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { submitTargetedRevisionRequest } from './review-revision-model.js';
|
|
2
|
-
import { beginInteractiveReview, abortInteractiveReview, readyInteractiveReview, failInteractiveReview } from './interactive-request.js';
|
|
2
|
+
import { beginInteractiveReview, abortInteractiveReview, readyInteractiveReview, failInteractiveReview, interactiveWaitingEvent } from './interactive-request.js';
|
|
3
3
|
import { localSourceHead, localWorkingHead } from './local-git-merge.js';
|
|
4
4
|
import { appendTaskComment } from './task-comments.js';
|
|
5
5
|
import { InMemoryStore } from './store.js';
|
|
@@ -7,7 +7,6 @@ import { openLocalManagedStore } from './local-managed-store.js';
|
|
|
7
7
|
import { relayStoreDirectory } from './relay-store.js';
|
|
8
8
|
import { normalizeThreadId } from './reviewer-thread.js';
|
|
9
9
|
import { publishTaskBlocked } from './cli-support.js';
|
|
10
|
-
import { eventFor } from './events.js';
|
|
11
10
|
import { classifyFailedTask, supersedeCancelledTask } from './task-actions.js';
|
|
12
11
|
import { requestTroubleshooterEscalation, resumeTroubleshooter } from './task-recovery.js';
|
|
13
12
|
import { adoptExistingPullRequestJob } from './cli-job-create.js';
|
|
@@ -117,7 +116,7 @@ export function createWorkspaceControl(deps) {
|
|
|
117
116
|
current.interactiveInvocation?.invocationId !== invocationId)
|
|
118
117
|
throw new Error('Stale interactive waiting request');
|
|
119
118
|
const reconciler = makeReconciler(store, concurrency);
|
|
120
|
-
const event =
|
|
119
|
+
const event = interactiveWaitingEvent(jobId, taskId, current.parentTaskId, executionId);
|
|
121
120
|
try {
|
|
122
121
|
const outcome = await reconciler.applyEvent(event);
|
|
123
122
|
if (!outcome.applied)
|
|
@@ -139,7 +138,7 @@ export function createWorkspaceControl(deps) {
|
|
|
139
138
|
if (command === 'review.interactive.ready')
|
|
140
139
|
return await readyInteractiveReview(store, jobId, taskId, executionId, invocationId, typeof body.revision === 'string' ? body.revision : '');
|
|
141
140
|
if (command === 'review.interactive.fail') {
|
|
142
|
-
const result = await failInteractiveReview(store, jobId, taskId, executionId, invocationId, typeof body.reason === 'string' ? body.reason : '
|
|
141
|
+
const result = await failInteractiveReview(store, jobId, taskId, executionId, invocationId, typeof body.reason === 'string' ? body.reason : 'Interactive review failed');
|
|
143
142
|
if (result.requeued)
|
|
144
143
|
await pool.reconcileLocalJob(jobId, 'interactive.preview-failed');
|
|
145
144
|
return result;
|
package/package.json
CHANGED
|
@@ -46,6 +46,30 @@ A Reviewer finding defects in a known immutable head emits `task.completed` with
|
|
|
46
46
|
|
|
47
47
|
For a failed Task, diagnose before retrying. Read `contracts/task-recovery-flows.md` for recovery and human escalation boundaries. Troubleshooter inspects the original Task via `task show` and paginated `task events`, verifies the root cause, then uses the pinned CLI `task recover --task-id ORIGINAL --recovery-task-id TROUBLESHOOTER` only after proving the repair. If a shared defect cannot be repaired in this execution, register it via `blocker add` on the owning P0/self Job and complete the recovery handoff; do not leave a worker running indefinitely. Only a genuinely human-required decision justifies the **pinned CLI** `task escalate --task-id TROUBLESHOOTER --required-action ... --resolution-condition ...`; this is a Relay operation, **not** an Events Bus event. Never invent or publish an escalation event, and never escalate a browser-readiness failure as a login request without authentication evidence. Only Relay can block/unblock a Troubleshooter; after a human response, recheck the blocker before recovering the original Task. Do not silently treat missing or stale evidence as success.
|
|
48
48
|
|
|
49
|
-
## 4.
|
|
49
|
+
## 4. Configured escalation and host-owned Interactive Review
|
|
50
|
+
|
|
51
|
+
`agents-relay escalation` executes the canonical Escalation Graph using only
|
|
52
|
+
`AGENTS_RELAY_ESCALATION_COMMAND` provided by the operator's environment. The
|
|
53
|
+
value is either an **absolute executable path** or a JSON argv array with an
|
|
54
|
+
absolute executable first (for example
|
|
55
|
+
`'["/opt/homebrew/bin/neo","escalation"]'` on a host explicitly using Neo).
|
|
56
|
+
Relay appends `--handoff-file`, optional `--on-needs-user-file` and `--cwd`.
|
|
57
|
+
No Shell expansion or default `neo` call is allowed. Missing or broken
|
|
58
|
+
configuration returns `technical_failure`; it must never be treated as
|
|
59
|
+
`resolved` or `needs_user`. This direct escalation command is distinct from
|
|
60
|
+
`task escalate`, which is the durable Troubleshooter/human-blocker transition.
|
|
61
|
+
|
|
62
|
+
For human Preview/Review, use the **existing** Relay
|
|
63
|
+
`review.interactive.begin/wait/ready/fail/abort` lifecycle. Relay provides the
|
|
64
|
+
execution-bound invocation and decision contract and emits a provider-neutral
|
|
65
|
+
`task.interactive_waiting` with `source.component: interactive-review`.
|
|
66
|
+
Preview media compilation, delivery (for example Markcut to Neo Mobile),
|
|
67
|
+
notifications, and UI are owned by the calling project/provider. Never invent
|
|
68
|
+
an approval from a compile receipt or a preview handoff, never replace the
|
|
69
|
+
exact event template with a provider-specific event, and never create an
|
|
70
|
+
unnecessary separate Preview Provider framework. Consult the project's own
|
|
71
|
+
Review/Preview contract for delivery and version binding.
|
|
72
|
+
|
|
73
|
+
## 5. Manage services when needed
|
|
50
74
|
|
|
51
75
|
For setup, outages, or persistent service health checks, load the separate `daemon-service-manage` Skill. The Relay Skill provides `bin/services.mjs`: run `node <pinned-skill-dir>/bin/services.mjs setup|status|doctor` as applicable. Do not start or restart services for ordinary Job operations, or create legacy unqualified PM2 names.
|
|
@@ -2,6 +2,16 @@
|
|
|
2
2
|
|
|
3
3
|
**Status:** Current recovery contract. Query Task state, recovery status, and comments through the matching Relay CLI.
|
|
4
4
|
|
|
5
|
+
The direct Escalation CLI has an **operator-selected executor**, configured
|
|
6
|
+
only through `AGENTS_RELAY_ESCALATION_COMMAND`. The canonical Graph maps
|
|
7
|
+
`resolved`, `failed` and `needs_user` results to durable workflow actions;
|
|
8
|
+
missing configuration or a failed/invalid provider result is a technical
|
|
9
|
+
failure, not proof that a human should be contacted. This is separate from
|
|
10
|
+
Relay's durable `task escalate` action, which the Troubleshooter may use only
|
|
11
|
+
when it has concrete evidence of an owner-only boundary. A Neo deployment may
|
|
12
|
+
select `["/opt/homebrew/bin/neo","escalation"]` as its executor, but Relay
|
|
13
|
+
cannot assume Neo exists. Never pass arbitrary Task text as a Shell command.
|
|
14
|
+
|
|
5
15
|
## Principles and ownership
|
|
6
16
|
|
|
7
17
|
- **Events Bus is neutral.** Its generic event envelope consists of event identity, type, time, and opaque client-defined data (plus any transport metadata needed by the bus). It must not understand Relay Jobs, Tasks, roles, or verdicts.
|