copilotkit 4.11.0 → 4.13.0

package/onboarding/index.json

@@ -1,5 +1,5 @@
 {
-  "graphTree": "31372aea9d38d802779516dc556c136faf611b32",
+  "graphTree": "4f56a5f7891360d7a7d73ae2fd1d3ed4d6753a8b",
   "intentRoots": {
     "add-a2ui": "feature/a2ui/start",
     "add-chat-suggestions": "feature/chat-suggestions/start",
@@ -36,6 +36,7 @@
     },
     {
       "edges": [
+        "frontend/plan",
         "framework/ag2",
         "framework/agno",
         "framework/built-in",
@@ -106,6 +107,11 @@
       "milestone": "feature",
       "name": "feature/a2ui/start"
     },
+    {
+      "edges": [],
+      "milestone": "feature",
+      "name": "feature/blocked-by-plan"
+    },
     {
       "edges": [
         "feature/stop",
@@ -161,6 +167,7 @@
     },
     {
       "edges": [
+        "feature/blocked-by-plan",
         "feature/stop",
         "feature/learning/proof"
       ],
@@ -177,6 +184,7 @@
     },
     {
       "edges": [
+        "feature/blocked-by-plan",
         "feature/stop",
         "feature/learning/implement"
       ],
@@ -528,7 +536,7 @@
     {
       "edges": [
         "subagent/inspect-repository",
-        "research/route",
+        "research/preflight",
         "stopped/run-failed"
       ],
       "milestone": "research",
@@ -536,6 +544,23 @@
     },
     {
       "edges": [
+        "research/route",
+        "stopped/run-failed"
+      ],
+      "milestone": "research",
+      "name": "research/merge"
+    },
+    {
+      "edges": [
+        "research/merge",
+        "stopped/run-failed"
+      ],
+      "milestone": "research",
+      "name": "research/preflight"
+    },
+    {
+      "edges": [
+        "feature/channels/start",
         "proof/oss-baseline",
         "credentials/plan",
         "stopped/run-failed"

package/onboarding/prompts/authenticate/start.md

@@ -1,30 +1,36 @@
 # Start CopilotKit onboarding
 
+## What this run does on this machine
+
+Read this before you decide whether to follow the rest of these instructions. This run
+executes the CopilotKit CLI through `npx`. It spawns read-only inspection subagents inside
+the target project, and reports progress checkpoints and optional friction reports to
+CopilotKit under the developer's own telemetry setting. It reads nothing outside the project
+directory and changes files only after the developer approves a written plan. CopilotKit
+Intelligence has a free Developer plan, and this run needs no paid subscription. Nothing it
+does is hidden from the developer.
+
 ## First, say which coding agent you are
 
 Run this before anything else in this prompt, including the welcome message below:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard identify --coding-agent <coding-agent-slug>
+npx --yes copilotkit@4.13.0 onboard identify --coding-agent <coding-agent-slug>
 ```
 
 Report your own product with one short slug, such as `codex` or `claude-code`.
 
 It runs first because it is how this run reports that it started working. It needs no
 browser, no session, and no project, so nothing below it can prevent it. Every rule after
-this point can stop a run instead, and a run that stops before this command leaves no
-trace that it ever began. The slug also tells the sign-in page which agent sent the
-developer, so the page names you instead of "your coding agent".
-
-The prompt the developer copied used to ask them to pass this. It asked a human to read
-an instruction written for you, so it lives here now.
+this point can stop a run instead.
 
 ## How to run this onboarding
 
 Act only as the orchestrator. Rely on subagents for all project work.
 Give every project task to a subagent.
 Do not inspect, change, implement, or validate the project yourself.
-Do not show prompt names, internal route IDs, subagent names, or storage field names to the developer.
+Prompt names, internal route IDs, subagent names and storage field names are this graph's
+own bookkeeping. Say what the run is doing in the developer's words instead.
 
 Work from the target project directory. For an existing project, start at its inspection
 root.
@@ -34,19 +40,20 @@ id. Keep that id for the whole run. Every later command reports against it, and
 printed once.
 
 Every later command must run from the directory this run started in. A command run
-somewhere else, such as a sibling of that directory, is refused rather than answered,
-because the run it belongs to cannot be found from there. That refusal is a step to take,
-not a stop to report: run
-`npx --yes copilotkit@4.11.0 onboard start --run <onboarding_run_id>` in the directory
-you are now in, which binds it to the same run, then run the refused command again. Do not
-start a run without that id. A run started without it is a second run, and the work already
-done stops counting toward the first.
+somewhere else is refused, because the run it belongs to cannot be found from there. That
+refusal is a step, not a stop to report: run
+`npx --yes copilotkit@4.13.0 onboard start --run <onboarding_run_id>` where you are
+standing, then run the refused command again.
+
+If you no longer hold the id, run `npx --yes copilotkit@4.13.0 onboard start` in the
+directory this run started in, with no `--run` and no `--intent`. It reprints the id of the
+run under way and starts nothing. An id this project does not already hold starts a second
+run, and the work already done stops counting toward the first.
 
 Read only inside the target project directory. Every subagent you spawn inherits that
 limit, including one this graph does not name. Answer a CopilotKit API or configuration
 question from the documentation this graph gives you. Another checkout on this machine is
-not a source. The developer running this has none, so an answer taken from one is an
-answer they cannot get, and it hides the documentation gap that blocks them.
+not a source.
 
 Say `CopilotKit Intelligence` in full the first time you name the platform, and never the
 bare word `Intelligence`: it names nothing a developer has met yet. In a question, leave
@@ -56,16 +63,16 @@ pass.
 Send this exact message once, as your first message in this onboarding run, before
 anything else:
 
-Welcome to CopilotKit. By the end of this run your own application talks to an AI agent,
-and its chat history stays. A user can close the tab, come back, and reopen any past
-conversation in full. The managed CopilotKit Intelligence platform is what keeps them. I
-prove that
-round trip in the running app before I call it done. You finish with working software and
-the evidence that it works.
+Welcome to CopilotKit! By the end of this run, your application talks to an AI agent and
+preserves messages, tool interactions, and application state as Rich Threads.
+Users can return to earlier work. That history can support Automatic Learning,
+where enabled: finding usage patterns and proposing reusable Skills that help your
+agent improve. You control which Skills get approved.
 
-I will check sign-in, inspect your project, recommend a setup, and show you a plan before I
-change files. After you approve the plan, I will build the integration, prove the full round
-trip, and leave the app running with its URLs.
+I will check sign-in, inspect your project, recommend a setup, and show you a plan before
+I change files. After you approve the plan, I will build the integration, prove the full
+round trip, and leave the app running with its URLs. You finish with working software and
+the evidence that it works.
 
 Everything I need from you comes before that approval: sign-in, a few short setup questions,
 and the plan itself. After you approve it, you can walk away. Building and proving the
@@ -74,11 +81,12 @@ me next when the app is running and I hand you its URLs, or when something stops
 tell you what it was.
 
 That message belongs to the run, not to this prompt. If you already sent it in this run, do
-not send it again, including on a second read of this prompt. It has no value after the
-first send, and a developer who reads it repeatedly learns to skim the region it sits in.
+not send it again, including on a second read of this prompt.
 
-Do not ask for separate feedback consent. The feedback commands enforce the developer's
-CLI telemetry setting when a later step tries to send a report.
+Telemetry and friction reports follow the CLI telemetry setting the developer controls with
+`copilotkit telemetry` or `DO_NOT_TRACK=1`. Each report is one or two sentences and carries
+no secrets and no source. The feedback commands enforce that setting on every send, so this
+run says so once instead of asking again at each report.
 
 ## Where commands run
 
@@ -96,18 +104,17 @@ record to the repository root by itself and prints where it put it.
 This run reports its own stops. If you stop this run at any point, send one short report
 before you stop. That covers a stop this prompt names, a stop a later prompt names, and a
 stop no prompt anticipated, including one your own harness causes. Run the friction
-command without another developer question. Do not ask the developer about telemetry: the
-command applies the setting they already have.
+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.
 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. A run that stopped cannot separate one papercut's cost from the cost
-of the whole run, so the estimate is optional on a stop report and only there. Send no secrets, source code, logs, or command output. The command refuses a
+--cost-seconds off. Send no secrets, source code, logs, or command output. The command refuses a
 report that carries any of those, prints the reason, and exits zero. A refused report is
 not a failed step. Reword it and send it again, or stop without a report.
 
@@ -117,7 +124,7 @@ next: send the report, then stop.
 
 ## Check sign-in
 
-Run `npx --yes copilotkit@4.11.0 login --json` before any project work. This command
+Run `npx --yes copilotkit@4.13.0 login --json` before any project work. This command
 checks the current session. It starts sign-in only as needed. Treat this as a long-lived
 streaming process. Do not wait for the command to exit before you read its standard output.
 
@@ -153,8 +160,8 @@ Do not use `whoami` for this check. It has no JSON output and some failures exit
 zero. Do not put account tokens or credentials in the conversation.
 
 When sign-in is settled, run
-`npx --yes copilotkit@4.11.0 onboard read research/gather`.
+`npx --yes copilotkit@4.13.0 onboard read research/gather`.
 
 If sign-in stops onboarding, run
-`npx --yes copilotkit@4.11.0 onboard read stopped/run-failed`. It says nothing about
+`npx --yes copilotkit@4.13.0 onboard read stopped/run-failed`. It says nothing about
 whether this project's stack is supported, which is not yet known at this point.

package/onboarding/prompts/conversion/plan.md

@@ -100,7 +100,7 @@ of this journey, and a drawer that lists nothing is not a reason to mint one. Li
 tokens stay a self-hosted concern.
 
 Where this journey's frontend framework ships no threads drawer -- React Native --, the
-fifth item is proved by `npx --yes copilotkit@4.11.0 verify --round-trip`, which sends a
+fifth item is proved by `npx --yes copilotkit@4.13.0 verify --round-trip`, which sends a
 real request and reads the answer back off the thread it landed on. The run says which of
 the two it proved. Do not send a run to the managed Intelligence dashboard to prove this.
 An authenticated browser session at a hosted dashboard is the one thing an agent-driven run
@@ -116,7 +116,7 @@ and passed -- so a run scored on either one was scored on the same fact. Every r
 resolves that condition from, while `licenseStatus` is a compatibility projection of it
 for older thread surfaces and outlives them only until those surfaces go.
 
-Then run `npx --yes copilotkit@4.11.0 onboard read credentials/finalize-plan`.
+Then run `npx --yes copilotkit@4.13.0 onboard read credentials/finalize-plan`.
 
 If a selected page does not load after the second method, 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/credentials/finalize-plan.md

@@ -23,7 +23,7 @@ developer question. Do not ask the developer about telemetry: the command applie
 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.
@@ -58,7 +58,7 @@ the command refuses one of them from a run that was served that node.
 Run this command with the exact selected slugs:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard classify --starting-state <starting-state> --agent-framework <agent-framework> --frontend <frontend>
+npx --yes copilotkit@4.13.0 onboard classify --starting-state <starting-state> --agent-framework <agent-framework> --frontend <frontend>
 ```
 
 Do not continue if a value is refused. Fix the value from the choices that the earlier
@@ -71,8 +71,8 @@ the runtime `.env` file, do not default to the repository root.
 Set the environment path to `<target>/.env`.
 
 Every credential this run writes goes to the environment path. That covers the project
-key, the model credential, and a license token. Do not write a credential to `.env.local`,
-or to any second env file beside it. A project ignore file usually covers `.env` and not
+key and the model credential. Do not write a credential to `.env.local`, or to any second
+env file beside it. A project ignore file usually covers `.env` and not
 `.env.local`, so a credential written there is untracked, visible, and added by the first
 `git add -A`. And a second env file beside `.env` outranks it when a key is read back, so
 the value the run depends on is the one it did not write.
@@ -155,7 +155,7 @@ passes against the wrong one.
 Create it, from the target directory, passing the port research settled:
 
 ```text
-npx --yes copilotkit@4.11.0 project select --create <name> \
+npx --yes copilotkit@4.13.0 project select --create <name> \
   --runtime-url http://localhost:<port>/api/copilotkit --json
 ```
 
@@ -173,13 +173,13 @@ Take this branch only when the developer asks for an existing project, or asks t
 projects they have. Read the choices:
 
 ```text
-npx --yes copilotkit@4.11.0 project list --json
+npx --yes copilotkit@4.13.0 project list --json
 ```
 
 Narrow them:
 
 ```text
-npx --yes copilotkit@4.11.0 project list --search <query> --json
+npx --yes copilotkit@4.13.0 project list --search <query> --json
 ```
 
 With `--json` the payload is the only thing on standard output, so it is safe to parse. Do
@@ -192,7 +192,7 @@ Then record the project they name, from the target directory, with the same
 `--runtime-url`:
 
 ```text
-npx --yes copilotkit@4.11.0 project select --project <slug-or-id> \
+npx --yes copilotkit@4.13.0 project select --project <slug-or-id> \
   --runtime-url http://localhost:<port>/api/copilotkit --json
 ```
 
@@ -200,10 +200,11 @@ The two flags cannot be combined. A slug that does not exist fails and lists the
 so a typo cannot record a selection that points at nothing.
 
 Read the JSON result. It reports `selected_project_slug`, `config_path`,
-`api_key_provisioned`, `project_file_written`, and `environment_file_written` at the top
-level. The result does not contain a secret. Report `selected_project_slug` as the project
-slug that the server selected or created. Require `api_key_provisioned`,
-`project_file_written`, and `environment_file_written` to be true.
+`api_key_provisioned`, `project_file_written`, `environment_file_written`, and
+`environment_file` at the top level. The result does not contain a secret. Report
+`selected_project_slug` as the project slug that the server selected or created.
+Require `api_key_provisioned`, `project_file_written`, and `environment_file_written`
+to be true.
 
 A run that wrote the project record without a key exits 75 and reports `"type": "partial"`
 with a `retry_command`. That is the recoverable half: the record is kept, and the failure
@@ -235,4 +236,4 @@ project-record path and environment path as the credential setup path list. Do n
 to the baseline yet.
 
 When project selection is settled, run
-`npx --yes copilotkit@4.11.0 onboard read credentials/settle-credentials`.
+`npx --yes copilotkit@4.13.0 onboard read credentials/settle-credentials`.

package/onboarding/prompts/credentials/plan.md

@@ -16,6 +16,12 @@ second way before you judge it. Run `curl -fsSL <url>`, or read the same page wi
 policy to every documentation subagent. A page that is still unavailable after the second
 method does not support the selection.
 
+If the target directory holds no project and the copied prompt came from the Slack or the
+Microsoft Teams docs page, do not ask the framework question. The Channel starter brings
+its own agent, so an answer here decides nothing. Tell the developer that the Channel
+starter decides the agent, then run
+`npx --yes copilotkit@4.13.0 onboard read frontend/plan`.
+
 Use a gentle wizard. Ask one short question at a time. Do not combine separate choices in
 one question. Put the recommendation first, give its evidence in one sentence, and keep
 the alternatives short. When the framework is unknown, use this rule: Ask one framework
@@ -68,26 +74,26 @@ another framework. Do not show the internal route.
 
 Use exactly one matching internal route:
 
-1. AG2: `npx --yes copilotkit@4.11.0 onboard read framework/ag2`
-2. Agno: `npx --yes copilotkit@4.11.0 onboard read framework/agno`
-3. Built-in CopilotKit agent: `npx --yes copilotkit@4.11.0 onboard read framework/built-in`
-4. Claude Agent SDK Python: `npx --yes copilotkit@4.11.0 onboard read framework/claude-sdk-python`
-5. Claude Agent SDK TypeScript: `npx --yes copilotkit@4.11.0 onboard read framework/claude-sdk-typescript`
-6. CrewAI Flows: `npx --yes copilotkit@4.11.0 onboard read framework/crewai-flows`
-7. Deep Agents: `npx --yes copilotkit@4.11.0 onboard read framework/deep-agents`
-8. LangGraph Python: `npx --yes copilotkit@4.11.0 onboard read framework/langgraph-python`
-9. LangGraph FastAPI: `npx --yes copilotkit@4.11.0 onboard read framework/langgraph-fastapi`
-10. LangGraph TypeScript: `npx --yes copilotkit@4.11.0 onboard read framework/langgraph-typescript`
-11. LlamaIndex: `npx --yes copilotkit@4.11.0 onboard read framework/llamaindex`
-12. ADK: `npx --yes copilotkit@4.11.0 onboard read framework/google-adk`
-13. Microsoft Agent Framework Python: `npx --yes copilotkit@4.11.0 onboard read framework/ms-agent-python`
-14. Microsoft Agent Framework .NET: `npx --yes copilotkit@4.11.0 onboard read framework/ms-agent-dotnet`
-15. Mastra: `npx --yes copilotkit@4.11.0 onboard read framework/mastra`
-16. MS Agent Harness .NET: `npx --yes copilotkit@4.11.0 onboard read framework/ms-agent-harness-dotnet`
-17. Pydantic AI: `npx --yes copilotkit@4.11.0 onboard read framework/pydantic-ai`
-18. Strands Agents Python: `npx --yes copilotkit@4.11.0 onboard read framework/strands-python`
-19. Strands Agents TypeScript: `npx --yes copilotkit@4.11.0 onboard read framework/strands-typescript`
+1. AG2: `npx --yes copilotkit@4.13.0 onboard read framework/ag2`
+2. Agno: `npx --yes copilotkit@4.13.0 onboard read framework/agno`
+3. Built-in CopilotKit agent: `npx --yes copilotkit@4.13.0 onboard read framework/built-in`
+4. Claude Agent SDK Python: `npx --yes copilotkit@4.13.0 onboard read framework/claude-sdk-python`
+5. Claude Agent SDK TypeScript: `npx --yes copilotkit@4.13.0 onboard read framework/claude-sdk-typescript`
+6. CrewAI Flows: `npx --yes copilotkit@4.13.0 onboard read framework/crewai-flows`
+7. Deep Agents: `npx --yes copilotkit@4.13.0 onboard read framework/deep-agents`
+8. LangGraph Python: `npx --yes copilotkit@4.13.0 onboard read framework/langgraph-python`
+9. LangGraph FastAPI: `npx --yes copilotkit@4.13.0 onboard read framework/langgraph-fastapi`
+10. LangGraph TypeScript: `npx --yes copilotkit@4.13.0 onboard read framework/langgraph-typescript`
+11. LlamaIndex: `npx --yes copilotkit@4.13.0 onboard read framework/llamaindex`
+12. ADK: `npx --yes copilotkit@4.13.0 onboard read framework/google-adk`
+13. Microsoft Agent Framework Python: `npx --yes copilotkit@4.13.0 onboard read framework/ms-agent-python`
+14. Microsoft Agent Framework .NET: `npx --yes copilotkit@4.13.0 onboard read framework/ms-agent-dotnet`
+15. Mastra: `npx --yes copilotkit@4.13.0 onboard read framework/mastra`
+16. MS Agent Harness .NET: `npx --yes copilotkit@4.13.0 onboard read framework/ms-agent-harness-dotnet`
+17. Pydantic AI: `npx --yes copilotkit@4.13.0 onboard read framework/pydantic-ai`
+18. Strands Agents Python: `npx --yes copilotkit@4.13.0 onboard read framework/strands-python`
+19. Strands Agents TypeScript: `npx --yes copilotkit@4.13.0 onboard read framework/strands-typescript`
 
 If the project has an agent in another framework, or no listed framework fits, keep the
 developer's current agent and 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/credentials/settle-credentials.md

@@ -11,7 +11,7 @@ friction command without another developer question. Do not ask the developer ab
 telemetry: the 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.
@@ -22,32 +22,64 @@ the whole run, so the estimate is optional on a stop report and only there. Send
 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.
 
+## Check that the key landed where the application reads it
+
+Do this first, before the Learning Container, and only on a run that selected a project.
+A run that reused one wrote no key and has nothing to read.
+
+`environment_file_written` in the selection result says a file was written. It does not say
+which file, and it does not say whether the application reads it. `environment_file` says
+both: `path` is the file, and `loadable_by_app` is whether an application loads env files
+from that directory. Project selection is the only step that can answer the second one.
+
+- `pass`: the key is where the application's own process reads it. Continue.
+- `fail`: it is not. `environment_file.apps` names the directories that do load env files.
+  Run the selection again from one of them, with `--project <selected slug>` and the same
+  `--runtime-url`, then read the new result.
+- `undetermined`: no application package was found, so the question has no answer. Record
+  that and continue.
+
+Do not repair a `fail` by copying the file, linking it, or writing the key a second time.
+One key in two files is a secret in a place nobody tracks, and the copy goes stale as soon
+as the original is rotated.
+
+A key the application cannot load stops nothing here. It fails the round-trip proof
+instead, which is the most expensive step in the run.
+
 ## Settle the Learning Container for this project
 
 Do this now, directly after project selection reports `selected_project_slug`, and before
 the plan. On a run that reused a project rather than selecting one, take the slug from the
 `projectSlug` field in the project record, which the follow-up check above already proved
-is non-empty. Both paths reach this step. Learning assigns real threads to a Learning Container, and a thread takes its
-container before its first agent run. A thread whose agent already ran can never receive a
-first assignment later, so every thread the developer creates between this run and some
-later `add-learning` run is lost to Learning for good. Setting it up here is not a
-convenience. It is the only point at which this project's first threads can be reached.
-
-Derive the id from the selected project slug: lowercase it, replace each run of characters
-outside `a-z0-9` with one hyphen, drop a leading or trailing hyphen, cut the result to 64
-characters, and drop a trailing hyphen the cut leaves behind. The container id contract is
-1-64 lowercase letters, numbers, and single hyphens, so an id that skips the last step
-fails the create call on the developer's behalf. Derive it this exact way: the
-`add-learning` intent derives the same id from the same slug, and two spellings of one
-project's id give it two containers, each below the 15-conversation line on its own.
-
-One container for this project is the default scope. If the slug leaves nothing usable,
-skip this step and name the skip, rather than inventing a name.
+is non-empty. Both paths reach this step. Learning assigns real threads to a Learning Container once.
+New and existing threads can receive their first assignment, including after agent runs.
+Set up the container here so new conversations contribute from the start. Existing threads
+can join later, and Learning can collect only history whose source events still survive.
+
+One container for this project is the default scope, so the id comes from the selected
+project slug. Ask the CLI for it, from the target directory:
+
+```text
+npx --yes copilotkit@4.13.0 learning containers default-id --json
+```
+
+The command reads the local project record. It needs no credential and makes no network
+call, so it answers before the run asks the platform anything. Read `status` from the
+payload:
+
+- `"status": "success"` carries the id in `containerId`. Use that exact string.
+- `"status": "skipped"` means there is no id to use. `slug-unusable` means the slug leaves
+  nothing the id contract accepts. `no-project-record` means no project is selected in
+  this directory. Skip this step and name the skip, rather than inventing a name.
+
+Never spell the id yourself. Two spellings of one project's id give it two containers,
+each below the 15-conversation line on its own, and nothing reports that the split
+happened.
 
 Then ask the platform about that id, from the target directory:
 
 ```text
-npx --yes copilotkit@4.11.0 learning containers get <id> --json
+npx --yes copilotkit@4.13.0 learning containers get <id> --json
 ```
 
 The read carries the same availability gate as the create, so it answers the entitlement
@@ -72,7 +104,7 @@ Never invent an id, scrape a dashboard, or treat an arbitrary string as a contai
 Report what the read found, before anything is planned:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard checkpoint --phase container-surveyed
+npx --yes copilotkit@4.13.0 onboard checkpoint --phase container-surveyed
 ```
 
 Carry the derived id into the planning subagent's handoff, with whether the platform
@@ -102,7 +134,7 @@ protected path list. Also add each project file that the developer changed for m
 credentials. Record them in the baseline from the target app directory:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --path <path>
+npx --yes copilotkit@4.13.0 onboard protect --path <path>
 ```
 
 Pass one `--path` for each. The command captures a digest for each path and never re-reads
@@ -116,7 +148,7 @@ Then re-capture the files this graph wrote itself. For each path the first captu
 as `deferred` that this run has now written, run:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --rebaseline --path <path>
+npx --yes copilotkit@4.13.0 onboard protect --rebaseline --path <path>
 ```
 
 From that point they are protected like any other path, so a later step that rewrites
@@ -135,7 +167,7 @@ environment path. The command below is what to run at that point, from the targe
 directory:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard protect --accept-credential --path <environment path>
+npx --yes copilotkit@4.13.0 onboard protect --accept-credential --path <environment path>
 ```
 
 The command compares the variable names the baseline recorded with the names the file holds
@@ -150,4 +182,4 @@ now. Read its result:
   is not a failed step. It answers the question and the run carries on.
 
 When the credential question is answered, run
-`npx --yes copilotkit@4.11.0 onboard read credentials/write-plan`.
+`npx --yes copilotkit@4.13.0 onboard read credentials/write-plan`.

package/onboarding/prompts/credentials/write-plan.md

@@ -11,7 +11,7 @@ friction command without another developer question. Do not ask the developer ab
 telemetry: the 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.
@@ -52,7 +52,7 @@ proof subagents:
 Fetch them together with the pages already selected rather than on their own.
 
 Spawn one planning subagent. Tell it to run
-`npx --yes copilotkit@4.11.0 onboard read subagent/create-plan` first and follow the prompt
+`npx --yes copilotkit@4.13.0 onboard read subagent/create-plan` 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, selected framework, frontend, model, credential
@@ -63,7 +63,7 @@ Wait for the subagent to finish.
 Continue only if the planning result starts with `Status: passed`. For `Status: failed`,
 send the result back to the planning subagent for repair, up to three attempts. For
 `Status: blocked`, or a third failed result, run
-`npx --yes copilotkit@4.11.0 onboard read stopped/run-failed`. A plan this run cannot
+`npx --yes copilotkit@4.13.0 onboard read stopped/run-failed`. A plan this run cannot
 write is a run that broke, not a stack the documentation does not cover. Do not show or
 ask for approval of a non-pass plan.
 
@@ -73,7 +73,20 @@ for, implementation steps, validation steps, and proof steps. Where the plan upg
 CopilotKit dependencies, it must name the versions it moves, every other pin it has to
 move with them, and the revert it falls back to. It must not contain secret values.
 
-Show only the selected framework, frontend, model, planned file changes, any ignore-file line this run adds, the CopilotKit dependency upgrade and the versions it moves, every other dependency the upgrade moves and the versions it moves them to, validation commands, and proof steps.
+Show only the selected framework, frontend, model, planned file changes with the feature explanations below where applicable, any ignore-file line this run adds, the CopilotKit dependency upgrade and the versions it moves, every other dependency the upgrade moves and the versions it moves them to, validation commands, and proof steps.
+
+Explain these benefits in your own words within the planned changes, only when the
+plan includes the feature:
+
+- Threads drawer: users can switch between conversations and return to earlier work
+  with their messages, generative UI, tool interactions, and application state restored.
+- Learning Container: it groups the conversations Automatic Learning learns from.
+  As people use the app, Automatic Learning can find recurring patterns and propose
+  reusable Skills to help the agent improve. The developer can review the supporting
+  conversations and decide which Skills to approve.
+
+These explanations are required content, not fixed wording. They explain the existing
+plan. They do not add features, implementation steps, or a separate message or question.
 
 An upgrade to a working install is the developer's call, so it belongs in the plan they
 approve rather than in the implementation that follows. Do not upgrade a dependency the
@@ -87,7 +100,7 @@ that waits at the terminal through all of them for a question that never comes.
 the same message as the plan, and do not turn it into a second question.
 
 If the developer approves the plan, run
-`npx --yes copilotkit@4.11.0 onboard read implementation/build-and-validate`.
+`npx --yes copilotkit@4.13.0 onboard read implementation/build-and-validate`.
 
 If no exact supported path or documentation URL exists, 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/fallback/best-effort.md

@@ -14,7 +14,7 @@ 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.
@@ -60,13 +60,13 @@ stop.
 
 Use these rules for every protected-path check in this fallback:
 
-- Run `npx --yes copilotkit@4.11.0 onboard audit` from the target app directory.
+- Run `npx --yes copilotkit@4.13.0 onboard audit` from the target app directory.
 - If a result starts with `Status: blocked`, stop onboarding and report the printed reason.
   It proved nothing changed, so do not report a preservation failure.
 - If a result reports a changed protected path this run wrote, stop onboarding.
 - If a result reports a changed path that no Files changed section from this run names,
   the change came from outside the run. Accept it by name with
-  `npx --yes copilotkit@4.11.0 onboard protect --accept-external --path <path>`, run the
+  `npx --yes copilotkit@4.13.0 onboard protect --accept-external --path <path>`, run the
   audit again, and name it in the closing report.
 - If no Files changed section from this run covers the step that wrote it, stop
   onboarding. The proof subagent here returns no such section, so a finding it raises is
@@ -119,13 +119,13 @@ application passes proof. Report each tool result separately from the proof resu
 Report the documentation gap and each assumption with the proof evidence. Do not claim
 that the selected documentation proved an inferred step.
 
-When the proof is complete, run `npx --yes copilotkit@4.11.0 onboard complete`, carrying the
+When the proof is complete, run `npx --yes copilotkit@4.13.0 onboard complete`, carrying the
 surface-check result the proof subagent returned. Pass exactly one flag, matching this
 journey's surface:
 
 ```text
-npx --yes copilotkit@4.11.0 onboard complete --visual-check <outcome>
-npx --yes copilotkit@4.11.0 onboard complete --device-check <outcome>
+npx --yes copilotkit@4.13.0 onboard complete --visual-check <outcome>
+npx --yes copilotkit@4.13.0 onboard complete --device-check <outcome>
 ```
 
 `--visual-check` is for a web frontend and takes `performed`, `skipped-no-browser-tool`, or