copilotkit 4.11.0 → 4.13.0

package/onboarding/prompts/frontend/angular.md

@@ -2,10 +2,10 @@
 
 Preserve an existing Angular frontend. Use the selected page for a new frontend.
 
-Use the starter shortcut only if all these facts are true: the target directory contains
-no entries, its name is a valid `init` project name, and the selected framework is ADK.
+Use the starter shortcut only if all these facts are true: the target directory holds no
+project, its name is a valid `init` project name, and the selected framework is ADK.
 If all three facts are true, record Angular as the selected frontend. Then run
-`npx --yes copilotkit@4.11.0 onboard read starter/clone` before you fetch documentation.
+`npx --yes copilotkit@4.13.0 onboard read starter/clone` before you fetch documentation.
 
 ## Documentation
 
@@ -63,7 +63,7 @@ you create or build an Angular project. If the installed version is lower, selec
 supported version first and use it for every later command in this project.
 
 If the pages support the selection, record Angular and these URLs. Then run
-`npx --yes copilotkit@4.11.0 onboard read credentials/finalize-plan`.
+`npx --yes copilotkit@4.13.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, or the two version lines do not fit
-together, run `npx --yes copilotkit@4.11.0 onboard read unsupported/no-validated-path`.
+together, run `npx --yes copilotkit@4.13.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/nextjs.md

@@ -2,7 +2,7 @@
 
 Preserve an existing Next.js frontend. Use the selected pages for a new frontend.
 
-Use the starter shortcut only if the target directory contains no entries and its name is
+Use the starter shortcut only if the target directory holds no project and its name is
 a valid `init` project name. The selected framework must also match one of these options.
 
 These Python options have Next.js starters: Agno, Claude Agent SDK Python, CrewAI Flows,
@@ -15,7 +15,7 @@ These TypeScript options have starters: Claude Agent SDK TypeScript, LangGraph T
 Mastra, and Strands Agents TypeScript. The .NET option is Microsoft Agent Framework .NET.
 
 If all shortcut conditions are true, record Next.js as the selected frontend. Then run
-`npx --yes copilotkit@4.11.0 onboard read starter/clone` before you fetch documentation.
+`npx --yes copilotkit@4.13.0 onboard read starter/clone` before you fetch documentation.
 
 ## Documentation
 
@@ -27,7 +27,7 @@ agent as the default agent, which is correct only for a project that has no agen
 Do not replace the developer's existing agent with the built-in agent.
 
 If the page supports the selection, record Next.js and this URL. Then run
-`npx --yes copilotkit@4.11.0 onboard read credentials/finalize-plan`.
+`npx --yes copilotkit@4.13.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --yes copilotkit@4.11.0 onboard read unsupported/no-validated-path`.
+`npx --yes copilotkit@4.13.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/plan.md

@@ -1,5 +1,19 @@
 # Select the frontend
 
+## A named Channel decides this node
+
+If the developer already named Slack or Microsoft Teams, use that choice.
+If the copied prompt came from a Slack or Teams docs page, use that page as the named frontend.
+
+Either one is final here. Do not ask the frontend question on that run. Do not let an
+existing frontend take a web route instead: the project keeps the frontend it has, and the
+Channel is what this run adds. Take the Slack or Microsoft Teams route below and name the
+provider to it. A Slack page names Slack. A Teams page names Teams.
+
+Every rule below is for a run that named neither.
+
+## Select the frontend from the findings
+
 Use the repository findings to select the frontend. Ask the developer only for choices
 that the repository does not show. Do not change application code in this phase.
 
@@ -9,9 +23,6 @@ the alternatives short. When the frontend is unknown, use this rule: Ask one fro
 question that lists the recommendation and valid choices. Do not ask a yes-or-no question
 first. Do not ask about the model or project in this step.
 
-If the developer already named Slack or Microsoft Teams, use that choice.
-If the copied prompt came from a Slack or Teams docs page, use that page as the named frontend.
-
 If the project has a frontend, preserve it and use the matching route below. If the project
 needs a frontend, show the valid choices and one recommendation based on repository
 evidence, then ask the developer to choose.
@@ -25,15 +36,15 @@ CopilotKit web apps. Then recommend the one the developer names, and say what ea
 
 Use exactly one matching internal route:
 
-1. React SPA: `npx --yes copilotkit@4.11.0 onboard read frontend/react-spa`
-2. Next.js: `npx --yes copilotkit@4.11.0 onboard read frontend/nextjs`
-3. Angular: `npx --yes copilotkit@4.11.0 onboard read frontend/angular`
-4. Vue 3: `npx --yes copilotkit@4.11.0 onboard read frontend/vue`
-5. React Native: `npx --yes copilotkit@4.11.0 onboard read frontend/react-native`
-6. Slack or Microsoft Teams: `npx --yes copilotkit@4.11.0 onboard read feature/channels/start`
+1. React SPA: `npx --yes copilotkit@4.13.0 onboard read frontend/react-spa`
+2. Next.js: `npx --yes copilotkit@4.13.0 onboard read frontend/nextjs`
+3. Angular: `npx --yes copilotkit@4.13.0 onboard read frontend/angular`
+4. Vue 3: `npx --yes copilotkit@4.13.0 onboard read frontend/vue`
+5. React Native: `npx --yes copilotkit@4.13.0 onboard read frontend/react-native`
+6. Slack or Microsoft Teams: `npx --yes copilotkit@4.13.0 onboard read feature/channels/start`
 
 If they chose Slack or Microsoft Teams, tell that node which one they chose so it
 does not ask again.
 
 If no listed frontend fits, run
-`npx --yes copilotkit@4.11.0 onboard read unsupported/no-validated-path`.
+`npx --yes copilotkit@4.13.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/react-native.md

@@ -15,7 +15,7 @@ documents `useRenderTool`, which is React Native's own hook for drawing a tool t
 already has. That is a different job and needs a tool in the agent.
 
 If the pages support the selection, record React Native and these URLs. Then run
-`npx --yes copilotkit@4.11.0 onboard read credentials/finalize-plan`.
+`npx --yes copilotkit@4.13.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --yes copilotkit@4.11.0 onboard read unsupported/no-validated-path`.
+`npx --yes copilotkit@4.13.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/react-spa.md

@@ -11,7 +11,7 @@ not move the agent into it.
 - https://docs.copilotkit.ai/react-spa.md
 
 If the page supports the selection, record React SPA and this URL. Then run
-`npx --yes copilotkit@4.11.0 onboard read credentials/finalize-plan`.
+`npx --yes copilotkit@4.13.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --yes copilotkit@4.11.0 onboard read unsupported/no-validated-path`.
+`npx --yes copilotkit@4.13.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/vue.md

@@ -16,7 +16,7 @@ page above. Vue has its own `useComponent`, which is not the React package. Take
 that reference page rather than from a Vue generative-UI guide, which is not published.
 
 If the pages support the selection, record Vue 3 and these URLs. Then run
-`npx --yes copilotkit@4.11.0 onboard read credentials/finalize-plan`.
+`npx --yes copilotkit@4.13.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --yes copilotkit@4.11.0 onboard read unsupported/no-validated-path`.
+`npx --yes copilotkit@4.13.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/implementation/build-and-validate.md

@@ -12,7 +12,7 @@ command without another developer question. Do not ask the developer about telem
 command applies the setting they already have.
 
 ```text
-npx --yes copilotkit@4.11.0 onboard friction --phase stop --category <slug>
+npx --yes copilotkit@4.13.0 onboard friction --phase stop --category <slug>
 ```
 
 Write one or two sentences to standard input: the step you stopped at and what stopped it.
@@ -36,6 +36,16 @@ plan said, what you did instead, and why. Carry that record into the closing sum
 which has an item for it. Do not stop for a departure that is the right call, and do not
 leave it unrecorded either.
 
+The existing agent's behavior is never a departure to record and carry on from. It is four
+things: its system prompt and instructions, its tools and what those tools do, its model
+and provider configuration, and its memory or state handling. Repair a failing check on
+the CopilotKit side first -- the frontend rendering, the tool schema, the runtime wiring.
+Where the only fix you can find is a change to the agent's instructions or tools, stop:
+report the failing predicate and the change you propose, and continue only after the
+developer approves it. An approved change is a behavior change, and the closing report
+names it as one. Never call a change to the agent's instructions or tools a repair. If you
+cannot ask, or the developer declines, use the route-out rules below.
+
 ## Authorization requested by the plan
 
 Approving the plan is the developer agreeing to every path it listed under
@@ -43,19 +53,24 @@ Approving the plan is the developer agreeing to every path it listed under
 app directory:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
+npx --yes copilotkit@4.13.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
 ```
 
 Consent has to be on the record before the file moves, so a call made after the change is
 refused. Continue only if every result starts with `Status: passed`. If the plan listed
 nothing there, skip this section.
 
+What you record here covers changing the file. It does not cover removing it. Never delete,
+move, or rename a protected path, whatever the plan says: the audit fails a path that is
+gone even when consent was recorded for it, and no command clears that. If a step cannot
+proceed without removing one, route out and report the path.
+
 If a path the plan listed has already changed, the developer changed it after the capture.
 No implementation step has run yet, so the change is theirs rather than this run's. Record
 consent over it by adding one flag:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>" --with-prior-change
+npx --yes copilotkit@4.13.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>" --with-prior-change
 ```
 
 The flag records their change as drift beside the consent, so the closing report names both
@@ -74,7 +89,7 @@ rather than this section.
 Run the audit from the target app directory:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard audit
+npx --yes copilotkit@4.13.0 onboard audit
 ```
 
 It compares every protected path with the digest the CLI captured for it. Its result starts
@@ -87,7 +102,7 @@ answers the same.
 
 Decide each path the audit names, one at a time.
 
-A path the audit lists under `Authorized to change:` is not a finding. The developer approved
+A path the audit lists under `Authorized to modify:` is not a finding. The developer approved
 it, the record says why, and the audit reports it rather than failing on it. Carry it into the
 summary with its reason. Nothing else is needed for it.
 
@@ -109,14 +124,14 @@ A path that no Files changed section names changed outside the run, and it is th
 developer's own file. Accept it by name:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --accept-external --path <path>
+npx --yes copilotkit@4.13.0 onboard protect --accept-external --path <path>
 ```
 
 A changed env file is its own case. This run asked the developer to place a credential
 there, so it takes the credential route rather than this one:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --accept-credential --path <path>
+npx --yes copilotkit@4.13.0 onboard protect --accept-credential --path <path>
 ```
 
 That route proves no recorded credential was lost, instead of taking the run's word that it
@@ -135,7 +150,7 @@ neither does a one-line fix. Never repair, reset, or revert it. Ask the develope
 the change, and record the answer they give:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
+npx --yes copilotkit@4.13.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
 ```
 
 Use it only for an answer a developer actually gave. It records the consent as taken
@@ -156,7 +171,7 @@ create it now, from the target app directory. The developer approved the id befo
 made, so this is the first point at which it can be created:
 
 ```text
-npx --yes copilotkit@4.11.0 learning containers create --id <id> --name <name> --json
+npx --yes copilotkit@4.13.0 learning containers create --id <id> --name <name> --json
 ```
 
 Pass the id the plan names. Take the name from the selected project's own display name, so
@@ -172,7 +187,7 @@ hold.
 Then report that the container is settled, before any edit:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard checkpoint --phase container-settled
+npx --yes copilotkit@4.13.0 onboard checkpoint --phase container-settled
 ```
 
 Where the plan names a container the platform already held, report the same checkpoint and
@@ -181,11 +196,11 @@ create nothing. Where the plan names no container, skip this section.
 Report the plan this run is about to implement:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard checkpoint --phase plan-written
+npx --yes copilotkit@4.13.0 onboard checkpoint --phase plan-written
 ```
 
 Spawn one implementation subagent. Tell it to run
-`npx --yes copilotkit@4.11.0 onboard read subagent/implement-and-validate` first and follow
+`npx --yes copilotkit@4.13.0 onboard read subagent/implement-and-validate` first and follow
 the prompt it returns. If that read fails because the subagent cannot use the shell, stop that
 subagent. Run the same command yourself, then spawn a fresh subagent with the returned prompt
 and the same handoff. Give it the plan, selected framework, frontend, model, exact target app
@@ -197,6 +212,14 @@ to implement every step in plan order and run the full validation list. Wait for
 One subagent implements the whole plan. Do not divide the work across concurrent subagents,
 and do not spawn a second subagent to reconcile a split.
 
+All implementation work happens in the run root's own working tree: the target app
+directory this run started in. Never send the subagent to a separate worktree, a branch
+checkout, or a copy of the project, and tell it to work in that directory itself. A
+subagent that worked elsewhere must bring its changes into the run root before it reports.
+The completion step verifies that the changed files exist in this project and refuses a run
+whose tree never changed, so work left in another tree ends the run with nothing in the
+developer's hands.
+
 If the implementation result does not start with `Status: passed`, do not continue to proof.
 Run the protected-path audit after the implementation subagent passes. Decide each path it
 names the same way as above, against the Files changed section that subagent just
@@ -205,11 +228,11 @@ returned. Continue to proof only when that audit passes.
 After the selected implementation path passes, report it:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard checkpoint --phase build-validated
+npx --yes copilotkit@4.13.0 onboard checkpoint --phase build-validated
 ```
 
 Then run
-`npx --yes copilotkit@4.11.0 onboard read proof/round-trip`.
+`npx --yes copilotkit@4.13.0 onboard read proof/round-trip`.
 
 ## Repair rules
 
@@ -231,9 +254,9 @@ the same command still fails after three repair attempts, or a result starts wit
 `Status: blocked`. A defect in a package this run installed is not a stack CopilotKit does
 not serve, a command this run cannot get to pass is not one either, and a blocked audit
 proved nothing about the stack. In those cases run
-`npx --yes copilotkit@4.11.0 onboard read stopped/run-failed`.
+`npx --yes copilotkit@4.13.0 onboard read stopped/run-failed`.
 
 A plan with no path to follow takes the unsupported ending: the fix requires changing the
 developer's existing agent or frontend, or the documentation does not support the plan. In
 those cases run
-`npx --yes copilotkit@4.11.0 onboard read unsupported/no-validated-path`.
+`npx --yes copilotkit@4.13.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/proof/complete.md

@@ -32,6 +32,12 @@ about it: keep this version pin, wire this constructor, run this build. It never
 as an account of hitting it. No count of what went wrong, no list of fixes made along the
 way, no argument that a failed check is not a defect.
 
+Where this run connected and proved Rich Threads, explain in your own words that they
+preserve messages, generative UI, tool interactions, and application state so users
+can return to earlier work. Explain that these interactions can also provide evidence
+for Automatic Learning. Describe only the capabilities supported by this run's result.
+This is required content within the handoff, not a separate message or a new check.
+
 The handoff must include:
 
 - The URL of the running app.
@@ -41,11 +47,19 @@ The handoff must include:
   installation. Do not open it. This item makes the developer aware the dashboard is
   there, and it is a sentence to write rather than a check to perform. Nothing in this
   graph gates on the dashboard, so a dashboard this run never opened is not a finding,
-  not a caveat, and not a blocker.
+  not a caveat, and not a blocker. Where this run settled a Learning Container, tell the
+  developer they can use their project there to follow progress, review Insights and
+  supporting conversations, and approve proposed Skills as they become available.
 - What changed since the developer approved the plan. Name every path, version, or step
   the run departed from, and why. A deviation can be the right call and still has to
   reach the person who approved the thing it departed from. Where nothing departed, say
   that in one line rather than leaving the item out.
+- Every change to the existing agent's behavior: its system prompt or instructions, its
+  tools or what those tools do, its model or provider configuration, or its memory or
+  state handling. Name each one, name the file, and say the developer approved it. Where
+  none of them changed, write `none` on that line rather than leaving the item out. Such a
+  change answers differently everywhere the agent is used, not only in CopilotKit, and the
+  developer is the only one who can tell whether that is wanted.
 - The process IDs and stop commands for the running agent and frontend.
 - The `@copilotkit/*` versions this conversion changed, and what they were before.
 - On a conversion, the criterion this run was judged against, in the words the run was
@@ -70,18 +84,24 @@ Name the debugging surface this journey's frontend can reach, rather than the on
 of the documentation leads with. For a web frontend it is the CopilotKit Inspector. For
 React Native there is no Inspector: it is a browser overlay built on a DOM custom element,
 and `@copilotkit/react-native` does not ship it. Give a mobile developer
-`npx --yes copilotkit@4.11.0 verify --round-trip`, the runtime's own log, the AG-UI
+`npx --yes copilotkit@4.13.0 verify --round-trip`, the runtime's own log, the AG-UI
 Event Inspector in the CopilotKit VS Code extension, and the CopilotKit Intelligence
 thread view
 instead. Naming the Inspector to a developer who cannot open it costs them the time it
 takes to conclude their own wiring is broken.
 
-Where this run settled a Learning Container, tell the developer what happens next, because
-a correct run looks like a broken one otherwise. Learning runs on its own: the first
-automatic run needs new threads from 15 distinct conversations in this container, and only
-the newest snapshot of each thread counts. A thread takes its container before its first
-agent run, so threads that ran before this change are never pulled in. The container starts
-empty on purpose.
+Where this run settled a Learning Container, explain in your own words that new
+conversations are routed to it, where Automatic Learning can find recurring patterns
+and propose reusable Skills to help the agent improve. The developer controls which
+Skills get approved. Explain that Learning results appear as new conversations provide
+enough evidence.
+
+These are required explanations within the existing handoff, not fixed wording or
+additional actions. Describe only the setup supported by this run's evidence. Do not
+claim this run produced Insights or Skills or configured automatic Skill delivery
+unless its evidence proves that. If no container was configured, report the actual
+reason and retain the project-management destination without implying that Learning
+is collecting evidence.
 
 Where the Learning step was skipped because this organization cannot use Learning, say so in
 one line and name what was not created. A skip nobody names reads as a container that
@@ -94,7 +114,7 @@ the friction commands without another developer question. Do not ask the develop
 telemetry: the command applies the setting they already have.
 
 ```text
-npx --yes copilotkit@4.11.0 onboard friction --category <slug> --cost-seconds <seconds>
+npx --yes copilotkit@4.13.0 onboard friction --category <slug> --cost-seconds <seconds>
 ```
 
 Write one or two sentences on the command's standard input. Pick one category from
@@ -106,7 +126,7 @@ Pass --docs-path only for a docs-missing or docs-wrong report, naming the page t
 is about:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard friction --category docs-wrong --cost-seconds 300 --docs-path /docs/threads/drawer
+npx --yes copilotkit@4.13.0 onboard friction --category docs-wrong --cost-seconds 300 --docs-path /docs/threads/drawer
 ```
 
 Give the page's site-relative path or its full URL, with no spaces, query string, or
@@ -123,14 +143,14 @@ Tell the developer when you send a friction report. Do not quote or summarize th
 unless the developer asks. If the CLI says the report was not sent,
 state what it said and continue without another question.
 
-When the evidence is gathered, run `npx --yes copilotkit@4.11.0 onboard complete`, carrying
+When the evidence is gathered, run `npx --yes copilotkit@4.13.0 onboard complete`, carrying
 the surface-check outcome the proof subagent returned. Pass exactly one flag, and pass the
 one that matches this journey's surface.
 
 For a web frontend -- React SPA, Next.js, Angular, Vue:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard complete --visual-check <outcome>
+npx --yes copilotkit@4.13.0 onboard complete --visual-check <outcome>
 ```
 
 The outcome is one of `performed`, `skipped-no-browser-tool`, `skipped-cloned-starter`, or
@@ -140,7 +160,7 @@ open no browser. It is the one skip that does not block.
 For React Native:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard complete --device-check <outcome>
+npx --yes copilotkit@4.13.0 onboard complete --device-check <outcome>
 ```
 
 The outcome is one of `performed`, `skipped-no-device`, `skipped-cloned-starter`, or
@@ -153,7 +173,7 @@ browser-origin CORS, so the flag you pass is how this run states which surface i
 For a web frontend, also pass the URL the browser opened:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard complete --visual-check <outcome> \
+npx --yes copilotkit@4.13.0 onboard complete --visual-check <outcome> \
   --frontend-url <the url you opened>
 ```
 
@@ -172,7 +192,7 @@ If the round trip proved and something after it still blocked this run, add `--b
 to the same command:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard complete --visual-check performed --blocked-by <cause>
+npx --yes copilotkit@4.13.0 onboard complete --visual-check performed --blocked-by <cause>
 ```
 
 The cause is one of `inspector` for a debugging surface that did not open,

package/onboarding/prompts/proof/oss-baseline.md

@@ -1,7 +1,7 @@
 # Prove the existing OSS baseline
 
 Do not prove the baseline yourself. Spawn one proof subagent. Tell it to run
-`npx --yes copilotkit@4.11.0 onboard read subagent/prove-oss-baseline` first and follow the
+`npx --yes copilotkit@4.13.0 onboard read subagent/prove-oss-baseline` first and follow the
 prompt it returns. If that read fails because the subagent cannot use the shell, stop that
 subagent. Run the same command yourself, then spawn a fresh subagent with the returned prompt
 and the same handoff. Give it the repository findings and exact CLI package spec.
@@ -17,7 +17,7 @@ Wait for the subagent to finish.
 Record what that proof returned before you route on it:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard proof --step oss-baseline --outcome <passed|failed|skipped> [--predicate <1-6>]
+npx --yes copilotkit@4.13.0 onboard proof --step oss-baseline --outcome <passed|failed|skipped> [--predicate <1-6>]
 ```
 
 Report the gate whatever it returned. Pass `passed` when the subagent proved a predicate,
@@ -35,12 +35,12 @@ Do not change project files before this proof ends. Starting existing developmen
 processes and their ignored runtime files is allowed.
 
 If the subagent proves the `both-oss` predicate, keep its evidence with the plan and run
-`npx --yes copilotkit@4.11.0 onboard read conversion/plan`. That project already works.
+`npx --yes copilotkit@4.13.0 onboard read conversion/plan`. That project already works.
 What it needs is the conversion, not a build.
 
 If the proof does not establish the baseline, record the starting state
 `both-copilotkit-unproved` and run
-`npx --yes copilotkit@4.11.0 onboard read credentials/plan`. This prompt is served
+`npx --yes copilotkit@4.13.0 onboard read credentials/plan`. This prompt is served
 whenever a project looks like an OSS integration, so a baseline that did not prove is an
 ordinary starting state rather than a failure. Keep the failing predicate with the plan.
 
@@ -54,5 +54,5 @@ and the plan preserves it rather than repeating it.
 
 If it cannot identify the running process safely, exposes a secret, or finds a baseline
 failure that cannot be classified, run
-`npx --yes copilotkit@4.11.0 onboard read stopped/run-failed`. None of those mean the
+`npx --yes copilotkit@4.13.0 onboard read stopped/run-failed`. None of those mean the
 project is unsupported: they mean this run did not establish what it needed to.

package/onboarding/prompts/proof/round-trip.md

@@ -1,7 +1,7 @@
 # Prove the user journey
 
 Do not do the proof work yourself. Spawn one proof subagent. Tell it to run
-`npx --yes copilotkit@4.11.0 onboard read subagent/prove-round-trip` first and follow the
+`npx --yes copilotkit@4.13.0 onboard read subagent/prove-round-trip` first and follow the
 prompt it returns. If that read fails because the subagent cannot use the shell, stop that
 subagent. Run the same command yourself, then spawn a fresh subagent with the returned prompt
 and the same handoff. Give it the selected framework, frontend, model, approved plan, selected
@@ -33,13 +33,13 @@ pass the time.
 Report each attempt at the journey as it ends, counting from one:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard checkpoint --phase journey-attempted --attempt 1
+npx --yes copilotkit@4.13.0 onboard checkpoint --phase journey-attempted --attempt 1
 ```
 
 Record what that proof returned before you route on it:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
+npx --yes copilotkit@4.13.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
 ```
 
 Report the gate whatever it returned. A proof that never ran is `skipped`, not failed. The
@@ -47,7 +47,7 @@ command prints one line and sends nothing else. Where a repair cycle runs the pr
 record each attempt as it ends.
 
 For every protected-path audit in this prompt, run
-`npx --yes copilotkit@4.11.0 onboard audit` from the target app directory. If its result
+`npx --yes copilotkit@4.13.0 onboard audit` from the target app directory. If its result
 starts with `Status: blocked`, report the printed reason and use the route-out rules below.
 A blocked audit proved nothing changed and is not a preservation failure. If a
 protected-path audit reports a changed path, decide it the way the implementation prompt
@@ -56,7 +56,7 @@ returns none, so a finding with no Files changed section to test against routes
 path one of those sections names is this run's own change and routes out too. Accept a
 path only when a section this run collected covers the step that wrote it and does not
 name it:
-`npx --yes copilotkit@4.11.0 onboard protect --accept-external --path <path>`. Then run
+`npx --yes copilotkit@4.13.0 onboard protect --accept-external --path <path>`. Then run
 the audit again and name the path in the closing summary. Never repair, reset, or revert a
 protected path.
 
@@ -64,12 +64,12 @@ That holds for a repair cycle too. When the fix for a failing check lands on a p
 path, the path is still the developer's, however right the diagnosis is and however small
 the fix. Reading the file never settles who wrote it. Ask the developer to allow the
 change, and record their answer with
-`npx --yes copilotkit@4.11.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"`,
+`npx --yes copilotkit@4.13.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"`,
 or route out. Never repair it, and never send it to a repair worker.
 
 If the proof result starts with `Status: passed`, run the protected-path audit. Continue to
 `proof/complete` only if that audit passes. After the audit passes, run
-`npx --yes copilotkit@4.11.0 onboard read proof/complete`. A performed surface outcome with
+`npx --yes copilotkit@4.13.0 onboard read proof/complete`. A performed surface outcome with
 the full round trip is core success even if a continued-development tool fails. A skipped
 surface outcome still enters `proof/complete` so the CLI records the blocked result. Do not
 describe a skipped surface as proved. Keep the Skills and MCP results separate from the proof
@@ -97,6 +97,17 @@ times. Use the route-out rules below for a blocked or third failed result.
 Enter the code-repair branch only for a source, configuration, dependency, or tracked-file
 defect.
 
+The existing agent's behavior stays outside that branch. It is four things: the agent's
+system prompt and instructions, its tools and what those tools do, its model and provider
+configuration, and its memory or state handling. Repair a failing proof on the CopilotKit
+side first -- the frontend rendering, the tool schema, the runtime wiring. Where the only
+fix the repair worker can find is a change to the agent's instructions or tools, it stops
+and returns the failing predicate with the change it proposes. Report both to the
+developer and send that repair only after they approve it. An approved change is a
+behavior change and the closing report names it as one. Never call a change to the agent's
+instructions or tools a repair, and never send one to a repair worker without that
+approval. If you cannot ask, or the developer declines, use the route-out rules below.
+
 If the starter shortcut created the selected path, spawn one repair subagent. Give it the
 failed step, proof evidence, generated path list, selected framework, frontend, model, exact
 target app directory, documentation, and policy.
@@ -125,7 +136,7 @@ Restart each project-owned process changed by the repair. Report the cycle, coun
 one:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard checkpoint --phase repair-attempted --attempt 1
+npx --yes copilotkit@4.13.0 onboard checkpoint --phase repair-attempted --attempt 1
 ```
 
 Then spawn a fresh proof subagent
@@ -143,18 +154,18 @@ and proof cycles.
 
 Route out only when the failure is not yours to fix, when the same proof still fails after
 three attempts, or when no evidence of the round trip can be produced. In those cases run
-`npx --yes copilotkit@4.11.0 onboard read stopped/run-failed`. The stack is supported:
+`npx --yes copilotkit@4.13.0 onboard read stopped/run-failed`. The stack is supported:
 this run did not finish, which is a different ending and a different report. All three are
 about the round trip itself. A round trip that proved is not one of them, whatever failed
 after it.
 
 If you stop here without taking that route -- a repair cycle you cannot finish, a limit in
 your own harness, a run that has run out -- send one short report before you stop. Run the
-friction command without another developer question. Do not ask the developer about
-telemetry: the command applies the setting they already have.
+friction command without another developer question: it applies the telemetry setting the
+developer already set.
 
 ```text
-npx --yes copilotkit@4.11.0 onboard friction --phase stop --category <slug>
+npx --yes copilotkit@4.13.0 onboard friction --phase stop --category <slug>
 ```
 
 Write one or two sentences to standard input: the step you stopped at and what stopped it.