copilotkit 4.16.0 → 4.18.0

package/onboarding/prompts/feature/open-generative-ui/proof.md

@@ -10,26 +10,46 @@ project-owned services running. Repair a failure caused by changed files and pro
 do not replace the output with a hard-coded component. If browser control is absent, report
 the missing visual proof honestly.
 
+Give the proof subagent the protected path list and the authorized list. Take that list from
+the latest audit, and copy the paths under `Authorized to modify:`. Tell it this rule: a fix
+can change a path on the authorized list. When a fix needs any other protected path, it must
+not edit it. It returns a result that starts with `Status: blocked` and names the file under
+Blockers.
+
+That result is a question for the developer. The file has not changed yet, so consent can
+still go on the record. Name the file and why the fix needs it, then end your turn and wait
+for the developer's answer. If they allow it, record their answer before any edit:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
+```
+
+Continue only when the result starts with `Status: passed`. Run the audit again, take the
+new list from its `Authorized to modify:` block, and spawn a fresh proof subagent with the
+same handoff and that list. A subagent that already returned cannot pick up consent recorded
+after it was spawned. If you cannot ask, or the developer declines, take the feature stop
+route below.
+
 Report each attempt at the proof as it ends, counting from one:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase journey-attempted --attempt 1
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase journey-attempted --attempt 1
 ```
 
 Report each repair cycle the same way, counting from one:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase repair-attempted --attempt 1
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase repair-attempted --attempt 1
 ```
 
 After the final attempt, report the gate exactly once:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
+npx --prefer-offline --yes copilotkit@4.18.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
 ```
 
 Use `passed` only for a proved generated UI, `failed` for an attempted proof that failed,
-and `skipped` when the proof could not run. Then run `npx --prefer-offline --yes copilotkit@4.16.0 onboard audit`.
+and `skipped` when the proof could not run. Then run `npx --prefer-offline --yes copilotkit@4.18.0 onboard audit`.
 Continue only when it starts with `Status: passed`.
 
 If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -37,16 +57,16 @@ with the proof subagent's `Files changed` section. If that section does not name
 run `onboard protect --accept-external --path <path>`, or
 `onboard protect --accept-credential --path <path>` for an env file where the developer
 placed a requested credential. If the subagent names the path, or its report does not settle
-who changed it, ask the developer to allow it. Only after they agree, run
-`onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"`.
-Run the audit again after each accepted or authorized change.
+who changed it, the change is this run's own, made without consent. Do not ask the developer
+to allow it: the CLI refuses consent for a path that already changed. Route out, and name
+the path and the change the audit reports. Run the audit again after each accepted change.
 
 If the audit still fails, or starts with `Status: blocked`, route out and stop:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/stop
+npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/stop
 ```
 
 When the audit passes, run
-`npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/complete` with the outcome actually
+`npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/complete` with the outcome actually
 observed.

package/onboarding/prompts/feature/open-generative-ui/start.md

@@ -3,10 +3,53 @@
 Treat this as a focused OSS enhancement. Orchestrate the work with separate read-only,
 implementation, and proof subagents, all restricted to the target project directory.
 
+## Waits, stops, and subagents
+
+A run that starts here has not read these rules yet, so they come first. They cover this
+prompt and every later one.
+
+Spawning a subagent returns almost at once. That return is the dispatch succeeding, not the
+work finishing: the result reaches you as a notification, or with the dispatch itself where
+your harness works that way. Do the work that does not depend on the result, then end your
+turn and wait for the result. That wait is a pause. Do not sleep or poll.
+
+A subagent that returns no usable result failed in your harness, not in this graph. Every
+assignment here is work you can do yourself, slower, so run that assignment yourself and
+carry on. Keep a read-only assignment read-only. If no subagent works at all, report it
+once:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase delegation-unavailable
+```
+
+Before you end your turn to wait for the developer, report the pause:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase awaiting-developer
+```
+
+A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
+When the answer or the result arrives, continue from the step that paused.
+
+If you stop this run, send one short report before you stop. The friction command follows
+the telemetry setting the developer already chose, so it needs no separate question.
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard friction --phase stop --category <slug> --message "<sentences>"
+```
+
+`--message` takes one or two sentences: the step you stopped at and what stopped it.
+Pick the category that fits from docs-missing, docs-wrong, docs-sequential, cli-gap,
+sdk-gap, environment, port-collision, credential, validation-loop, and other. Leave
+--cost-seconds off. Send no secrets, source code, logs, or command output. A refused report
+is not a failed step: reword it and send it again, or stop without a report. A stop that
+routes to `feature/stop` sends no report here: that prompt first asks the developer about
+one scoped fix, and sends the report itself when no fix is approved.
+
 Before any subagent or project process runs, capture the developer's existing work:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect
 ```
 
 Keep the exact protected path list it prints and give that list to every subagent. No
@@ -16,15 +59,13 @@ approved authorization before implementation.
 Before edits, have a research subagent identify the current CopilotKit runtime route,
 provider/chat component, agent id, package versions, existing middleware, sandbox/CSP
 constraints, and normal test/dev commands. Prove the existing app first with `/info`,
-`npx --prefer-offline --yes copilotkit@4.16.0 verify --expect-runtime oss --round-trip --agent <agent-id> --json`,
-and a real frontend request when browser control is available. If the app is not an existing
-OSS CopilotKit app with a proven round trip, change nothing and direct the developer to the
-generic onboarding path first.
+`npx --prefer-offline --yes copilotkit@4.18.0 verify --expect-runtime oss --round-trip --agent <agent-id> --json`,
+and a real frontend request when browser control is available.
 
 Wait for the inspection subagent to finish. Then report that the inspection came back:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase research-returned
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase research-returned
 ```
 
 A refused checkpoint prints its reason and leaves onboarding unaffected. It is not a
@@ -34,7 +75,7 @@ If the inspection did not prove the baseline this intent extends, stop here with
 changing files:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/stop
+npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/stop
 ```
 
 Do not sign in, select an Intelligence project, create credentials, change the existing
@@ -56,7 +97,7 @@ one.
 After approval, record each approved path before implementation:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
 ```
 
 If an approved path changed after capture and no implementation step has run, add
@@ -66,7 +107,7 @@ authorize a path the approved plan did not list.
 Then report the plan this run is about to implement:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase plan-written
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase plan-written
 ```
 
-Then run `npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/open-generative-ui/implement`.
+Then run `npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/open-generative-ui/implement`.

package/onboarding/prompts/feature/realtime-sync/implement.md

@@ -17,14 +17,45 @@ non-zero on an app that is working. Pass what `identifyUser` reads with a repeat
 It is not a defect to repair.
 
 Run focused tests and
-`npx --prefer-offline --yes copilotkit@4.16.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
+`npx --prefer-offline --yes copilotkit@4.18.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
 Repair changed-file failures and record changed paths and secret-safe validation
 evidence.
 
+Before you spawn the implementation subagent, take the authorized list from the CLI:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard audit
+```
+
+From its result, copy the paths under `Authorized to modify:`. A passed or failed audit with
+no such block means that nothing is authorized. Read only that block now, and decide the
+findings of a failed audit after implementation, with the audit rules below. If this audit
+starts with `Status: blocked`, the CLI cannot supply the list. Report the printed reason and
+take the feature stop route below.
+
+Give the implementation subagent the protected path list and the authorized list. Tell it
+this rule: it can change a path on the authorized list. When the work needs any other
+protected path, it must not edit it. It returns a result that starts with `Status: blocked`
+and names the file under Blockers.
+
+That result is a question for the developer. The file has not changed yet, so consent can
+still go on the record. Name the file and why the work needs it, then end your turn and wait
+for the developer's answer. If they allow it, record their answer before any edit:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
+```
+
+Continue only when the result starts with `Status: passed`. Run the audit again, take the
+new list from its `Authorized to modify:` block, and spawn a fresh implementation subagent
+with the same handoff and that list. A subagent that already returned cannot pick up consent
+recorded after it was spawned. If you cannot ask, or the developer declines, take the
+feature stop route below.
+
 After validation and each repair, run:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard audit
+npx --prefer-offline --yes copilotkit@4.18.0 onboard audit
 ```
 
 Continue only when it starts with `Status: passed`. A path under `Authorized to modify:` is
@@ -35,33 +66,30 @@ with the implementation subagent's `Files changed` section. If that section does
 the path, accept the developer's external change:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect --accept-external --path <path>
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --accept-external --path <path>
 ```
 
 For an env file where the developer placed a requested credential, use
 `onboard protect --accept-credential --path <path>` instead. If the subagent names the path,
-or its report does not settle who changed it, ask the developer to allow the unplanned
-change. Only after they agree, record their answer:
-
-```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
-```
+or its report does not settle who changed it, the change is this run's own, made without
+consent. Do not ask the developer to allow it: the CLI refuses consent for a path that
+already changed. Route out, and name the path and the change the audit reports.
 
-Run the audit again after each accepted or authorized change. If it still fails, or starts
+Run the audit again after each accepted change. If it still fails, or starts
 with `Status: blocked`, route out and stop:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/stop
+npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/stop
 ```
 
 When implementation validation passes, report it:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase build-validated
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase build-validated
 ```
 
 If validation cannot pass, or this intent needs a prerequisite the app does not have, use
 the feature stop route above without further changes.
 
 Otherwise run
-`npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/realtime-sync/proof`.
+`npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/realtime-sync/proof`.

package/onboarding/prompts/feature/realtime-sync/proof.md

@@ -4,33 +4,54 @@ Delegate proof to a fresh subagent. Open the same authenticated project/thread i
 browser contexts. From context A, create or mutate a thread and send a message. Require
 context B to receive the thread/message change without a manual reload. Then exercise a
 second mutation in the reverse direction where the product supports it. Keep the managed
-round-trip verification green.
+round-trip verification result that implementation recorded: passed, or UNKNOWN for an
+auth-gated app.
 
 Record both visible states, actions, timing, app URL, process IDs, and safe stop commands.
 A successful WebSocket connection, a server event, or a refreshed second tab is not proof.
 Repair changed-file defects and repeat. If the environment cannot drive two contexts, report
 the missing proof rather than claiming realtime works.
 
+Give the proof subagent the protected path list and the authorized list. Take that list from
+the latest audit, and copy the paths under `Authorized to modify:`. Tell it this rule: a fix
+can change a path on the authorized list. When a fix needs any other protected path, it must
+not edit it. It returns a result that starts with `Status: blocked` and names the file under
+Blockers.
+
+That result is a question for the developer. The file has not changed yet, so consent can
+still go on the record. Name the file and why the fix needs it, then end your turn and wait
+for the developer's answer. If they allow it, record their answer before any edit:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
+```
+
+Continue only when the result starts with `Status: passed`. Run the audit again, take the
+new list from its `Authorized to modify:` block, and spawn a fresh proof subagent with the
+same handoff and that list. A subagent that already returned cannot pick up consent recorded
+after it was spawned. If you cannot ask, or the developer declines, take the feature stop
+route below.
+
 Report each attempt at the proof as it ends, counting from one:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase journey-attempted --attempt 1
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase journey-attempted --attempt 1
 ```
 
 Report each repair cycle the same way, counting from one:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase repair-attempted --attempt 1
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase repair-attempted --attempt 1
 ```
 
 After the final attempt, report the gate exactly once:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
+npx --prefer-offline --yes copilotkit@4.18.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
 ```
 
 Use `passed` only for proved two-client sync, `failed` for an attempted proof that failed,
-and `skipped` when the proof could not run. Then run `npx --prefer-offline --yes copilotkit@4.16.0 onboard audit`.
+and `skipped` when the proof could not run. Then run `npx --prefer-offline --yes copilotkit@4.18.0 onboard audit`.
 Continue only when it starts with `Status: passed`.
 
 If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -38,15 +59,15 @@ with the proof subagent's `Files changed` section. If that section does not name
 run `onboard protect --accept-external --path <path>`, or
 `onboard protect --accept-credential --path <path>` for an env file where the developer
 placed a requested credential. If the subagent names the path, or its report does not settle
-who changed it, ask the developer to allow it. Only after they agree, run
-`onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"`.
-Run the audit again after each accepted or authorized change.
+who changed it, the change is this run's own, made without consent. Do not ask the developer
+to allow it: the CLI refuses consent for a path that already changed. Route out, and name
+the path and the change the audit reports. Run the audit again after each accepted change.
 
 If the audit still fails, or starts with `Status: blocked`, route out and stop:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/stop
+npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/stop
 ```
 
 When the audit passes, run
-`npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/complete` with the actual outcome.
+`npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/complete` with the actual outcome.

package/onboarding/prompts/feature/realtime-sync/start.md

@@ -4,10 +4,53 @@ Treat realtime sync as the Intelligence thread-realtime plane, not as a generic
 exercise. Act as the orchestrator and delegate read-only inspection, implementation, and
 two-context proof to subagents within the target project.
 
+## Waits, stops, and subagents
+
+A run that starts here has not read these rules yet, so they come first. They cover this
+prompt and every later one.
+
+Spawning a subagent returns almost at once. That return is the dispatch succeeding, not the
+work finishing: the result reaches you as a notification, or with the dispatch itself where
+your harness works that way. Do the work that does not depend on the result, then end your
+turn and wait for the result. That wait is a pause. Do not sleep or poll.
+
+A subagent that returns no usable result failed in your harness, not in this graph. Every
+assignment here is work you can do yourself, slower, so run that assignment yourself and
+carry on. Keep a read-only assignment read-only. If no subagent works at all, report it
+once:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase delegation-unavailable
+```
+
+Before you end your turn to wait for the developer, report the pause:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase awaiting-developer
+```
+
+A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
+When the answer or the result arrives, continue from the step that paused.
+
+If you stop this run, send one short report before you stop. The friction command follows
+the telemetry setting the developer already chose, so it needs no separate question.
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard friction --phase stop --category <slug> --message "<sentences>"
+```
+
+`--message` takes one or two sentences: the step you stopped at and what stopped it.
+Pick the category that fits from docs-missing, docs-wrong, docs-sequential, cli-gap,
+sdk-gap, environment, port-collision, credential, validation-loop, and other. Leave
+--cost-seconds off. Send no secrets, source code, logs, or command output. A refused report
+is not a failed step: reword it and send it again, or stop without a report. A stop that
+routes to `feature/stop` sends no report here: that prompt first asks the developer about
+one scoped fix, and sends the report itself when no fix is approved.
+
 Before any subagent or project process runs, capture the developer's existing work:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect
 ```
 
 Keep the exact protected path list it prints and give that list to every subagent. No
@@ -17,13 +60,12 @@ approved authorization before implementation.
 Before edits, inspect the current runtime, provider/chat, agent id, authenticated stable user
 identity, thread routes, existing Intelligence configuration (presence only), current websocket
 configuration, and normal test/dev commands. Prove the current frontend-to-runtime-to-agent
-round trip and inspect `/info`. If this is not an existing CopilotKit app, leave files
-unchanged and direct the developer to generic onboarding first.
+round trip and inspect `/info`.
 
 Wait for the inspection subagent to finish. Then report that the inspection came back:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase research-returned
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase research-returned
 ```
 
 A refused checkpoint prints its reason and leaves onboarding unaffected. It is not a
@@ -33,11 +75,11 @@ If the inspection did not prove the baseline this intent extends, stop here with
 changing files:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/stop
+npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/stop
 ```
 
 Fetch the current official guides before planning:
-https://docs.copilotkit.ai/intelligence/connect-your-runtime.md
+https://docs.copilotkit.ai/intelligence/quickstart.md
 https://docs.copilotkit.ai/auth.md
 https://docs.copilotkit.ai/intelligence/threads-explained.md
 https://docs.copilotkit.ai/reference/hooks/useThreads.md
@@ -59,7 +101,7 @@ one.
 After approval, record each approved path before implementation:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
 ```
 
 If an approved path changed after capture and no implementation step has run, add
@@ -69,7 +111,7 @@ authorize a path the approved plan did not list.
 Then report the plan this run is about to implement:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase plan-written
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase plan-written
 ```
 
-Then run `npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/realtime-sync/implement`.
+Then run `npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/realtime-sync/implement`.

package/onboarding/prompts/feature/rich-threads/implement.md

@@ -2,7 +2,7 @@
 
 Delegate implementation to one subagent with the approved plan and fetched official guides.
 If repository evidence does not prove an existing valid Intelligence selection, run
-`npx --prefer-offline --yes copilotkit@4.16.0 login --json` and follow its single streaming session. Then
+`npx --prefer-offline --yes copilotkit@4.18.0 login --json` and follow its single streaming session. Then
 list projects, show the developer the current/recent choices, and select or create one only
 after they choose. Require the secret-safe selection summary to confirm the project file,
 environment file, and key provisioning; never display a key. If existing configuration is
@@ -20,14 +20,45 @@ non-zero on an app that is working. Pass what `identifyUser` reads with a repeat
 It is not a defect to repair.
 
 Run focused type/test commands, then start the app and run
-`npx --prefer-offline --yes copilotkit@4.16.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
+`npx --prefer-offline --yes copilotkit@4.18.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
 Repair changed-file failures before continuing. Record changed paths and secret-safe
 validation evidence.
 
+Before you spawn the implementation subagent, take the authorized list from the CLI:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard audit
+```
+
+From its result, copy the paths under `Authorized to modify:`. A passed or failed audit with
+no such block means that nothing is authorized. Read only that block now, and decide the
+findings of a failed audit after implementation, with the audit rules below. If this audit
+starts with `Status: blocked`, the CLI cannot supply the list. Report the printed reason and
+take the feature stop route below.
+
+Give the implementation subagent the protected path list and the authorized list. Tell it
+this rule: it can change a path on the authorized list. When the work needs any other
+protected path, it must not edit it. It returns a result that starts with `Status: blocked`
+and names the file under Blockers.
+
+That result is a question for the developer. The file has not changed yet, so consent can
+still go on the record. Name the file and why the work needs it, then end your turn and wait
+for the developer's answer. If they allow it, record their answer before any edit:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
+```
+
+Continue only when the result starts with `Status: passed`. Run the audit again, take the
+new list from its `Authorized to modify:` block, and spawn a fresh implementation subagent
+with the same handoff and that list. A subagent that already returned cannot pick up consent
+recorded after it was spawned. If you cannot ask, or the developer declines, take the
+feature stop route below.
+
 After validation and each repair, run:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard audit
+npx --prefer-offline --yes copilotkit@4.18.0 onboard audit
 ```
 
 Continue only when it starts with `Status: passed`. A path under `Authorized to modify:` is
@@ -38,33 +69,30 @@ with the implementation subagent's `Files changed` section. If that section does
 the path, accept the developer's external change:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect --accept-external --path <path>
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --accept-external --path <path>
 ```
 
 For an env file where the developer placed a requested credential, use
 `onboard protect --accept-credential --path <path>` instead. If the subagent names the path,
-or its report does not settle who changed it, ask the developer to allow the unplanned
-change. Only after they agree, record their answer:
-
-```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
-```
+or its report does not settle who changed it, the change is this run's own, made without
+consent. Do not ask the developer to allow it: the CLI refuses consent for a path that
+already changed. Route out, and name the path and the change the audit reports.
 
-Run the audit again after each accepted or authorized change. If it still fails, or starts
+Run the audit again after each accepted change. If it still fails, or starts
 with `Status: blocked`, route out and stop:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/stop
+npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/stop
 ```
 
 When implementation validation passes, report it:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase build-validated
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase build-validated
 ```
 
 If validation cannot pass, or this intent needs a prerequisite the app does not have, use
 the feature stop route above without further changes.
 
 Otherwise run
-`npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/rich-threads/proof`.
+`npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/rich-threads/proof`.

package/onboarding/prompts/feature/rich-threads/proof.md

@@ -3,34 +3,55 @@
 Delegate proof to a fresh subagent. In the real authenticated frontend, create a conversation,
 send a distinct message, confirm the response, reload or reopen the same thread, and require
 the prior history to remain visible for that same stable user. Confirm the runtime exposes
-the required thread routes and the Intelligence verification remains successful.
+the required thread routes and the Intelligence verification keeps the result that
+implementation recorded: passed, or UNKNOWN for an auth-gated app.
 
 Record the interaction, visible persisted history, app URL, process IDs, and safe stop
 commands. Do not count a thread id in a log, a successful API call, or an in-memory history
 as proof. Repair defects caused by changed files and repeat. Keep project-owned servers
 running.
 
+Give the proof subagent the protected path list and the authorized list. Take that list from
+the latest audit, and copy the paths under `Authorized to modify:`. Tell it this rule: a fix
+can change a path on the authorized list. When a fix needs any other protected path, it must
+not edit it. It returns a result that starts with `Status: blocked` and names the file under
+Blockers.
+
+That result is a question for the developer. The file has not changed yet, so consent can
+still go on the record. Name the file and why the fix needs it, then end your turn and wait
+for the developer's answer. If they allow it, record their answer before any edit:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
+```
+
+Continue only when the result starts with `Status: passed`. Run the audit again, take the
+new list from its `Authorized to modify:` block, and spawn a fresh proof subagent with the
+same handoff and that list. A subagent that already returned cannot pick up consent recorded
+after it was spawned. If you cannot ask, or the developer declines, take the feature stop
+route below.
+
 Report each attempt at the proof as it ends, counting from one:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase journey-attempted --attempt 1
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase journey-attempted --attempt 1
 ```
 
 Report each repair cycle the same way, counting from one:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase repair-attempted --attempt 1
+npx --prefer-offline --yes copilotkit@4.18.0 onboard checkpoint --phase repair-attempted --attempt 1
 ```
 
 After the final attempt, report the gate exactly once:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
+npx --prefer-offline --yes copilotkit@4.18.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
 ```
 
 Use `passed` only for proved persistence and reopen, `failed` for an attempted proof that
 failed, and `skipped` when the proof could not run. Then run
-`npx --prefer-offline --yes copilotkit@4.16.0 onboard audit`. Continue only when it starts with
+`npx --prefer-offline --yes copilotkit@4.18.0 onboard audit`. Continue only when it starts with
 `Status: passed`.
 
 If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -38,16 +59,16 @@ with the proof subagent's `Files changed` section. If that section does not name
 run `onboard protect --accept-external --path <path>`, or
 `onboard protect --accept-credential --path <path>` for an env file where the developer
 placed a requested credential. If the subagent names the path, or its report does not settle
-who changed it, ask the developer to allow it. Only after they agree, run
-`onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"`.
-Run the audit again after each accepted or authorized change.
+who changed it, the change is this run's own, made without consent. Do not ask the developer
+to allow it: the CLI refuses consent for a path that already changed. Route out, and name
+the path and the change the audit reports. Run the audit again after each accepted change.
 
 If the audit still fails, or starts with `Status: blocked`, route out and stop:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/stop
+npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/stop
 ```
 
 When the audit passes, run
-`npx --prefer-offline --yes copilotkit@4.16.0 onboard read feature/complete` with the actual browser
+`npx --prefer-offline --yes copilotkit@4.18.0 onboard read feature/complete` with the actual browser
 outcome.