copilotkit 4.29.0 → 4.30.0

package/onboarding/prompts/framework/deep-agents.md

@@ -1,19 +1,13 @@
 # Configure Deep Agents
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing Deep Agents language and model setup. For a new agent, use the vendor
 that the framework step recorded. Use OpenAI only when the record and this conversation
-have no vendor. This release offers a new agent on this framework OpenAI or an
-OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or
-Google, say that this release supports OpenAI or an OpenAI-compatible provider on this
-framework, that Anthropic and Google come in a later release, and offer the built-in
-CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor
-and model. If it runs on Anthropic or Google, add one line to the plan: the page context
-that CopilotKit sends can fail with that vendor until a CopilotKit SDK release fixes it
-(PE-728). Take that vendor's package, class, and credential variable names from the
+have no vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or Google, say that this release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic and Google come in a later release, and offer the built-in CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor
+and model. If it runs on Anthropic or Google, add one line to the plan: this CopilotKit CLI release has not proven Anthropic or Google on this framework, so a chat can fail with it. Take that vendor's package, class, and credential variable names from the
 framework's own documentation, and use a model id that the vendor serves to a new key
 today. For an OpenAI-compatible provider, keep `OPENAI_API_KEY`, use the model id that
 `setup/questions` recorded, and write the base URL that `setup/questions` recorded as
@@ -51,7 +45,7 @@ Record the selected framework, language, vendor, model, required credential vari
 names, these URLs, and how the agent reads `context`.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/google-adk.md

@@ -1,15 +1,11 @@
 # Configure ADK
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing ADK model setup. For a new agent, use the recorded vendor. Use Google
-only when the record and this conversation have no vendor. This release runs ADK on
-Google, OpenAI, or an OpenAI-compatible provider. For a new agent, if the developer names
-Anthropic, say that this release supports Google, OpenAI, or an OpenAI-compatible provider
-on ADK, that Anthropic comes in a later release, and offer the built-in CopilotKit agent
-if they need Anthropic now. An existing agent keeps its vendor and model. Take that
+only when the record and this conversation have no vendor. Google, OpenAI, an OpenAI-compatible provider, and Anthropic work. An existing agent keeps its vendor and model. Take that
 vendor's package, class, and credential variable names from the framework's own
 documentation, and use a model id that the vendor serves to a new key today. For an
 OpenAI-compatible provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions`
@@ -43,7 +39,7 @@ Record the selected framework, vendor, model, required credential variable names
 these URLs.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/langgraph-fastapi.md

@@ -1,18 +1,12 @@
 # Configure LangGraph FastAPI
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing LangGraph FastAPI model setup. For a new agent, use the vendor that
 the framework step recorded. Use OpenAI only when the record and this conversation have no
-vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible
-provider only. For a new agent, if the developer names Anthropic or Google, say that this
-release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic
-and Google come in a later release, and offer the built-in CopilotKit agent if they need
-Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on
-Anthropic or Google, add one line to the plan: the page context that CopilotKit sends can
-fail with that vendor until a CopilotKit SDK release fixes it (PE-728). Take that vendor's
+vendor. OpenAI, an OpenAI-compatible provider, Anthropic, and Google work. An existing agent keeps its vendor and model. Take that vendor's
 package, class, and credential variable names from the framework's own documentation, and
 use a model id that the vendor serves to a new key today. For an OpenAI-compatible
 provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and
@@ -43,7 +37,7 @@ Record the selected framework, vendor, model, required credential variable names
 these URLs.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/langgraph-python.md

@@ -1,18 +1,12 @@
 # Configure LangGraph Python
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing LangGraph Python model setup. For a new agent, use the vendor that
 the framework step recorded. Use OpenAI only when the record and this conversation have no
-vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible
-provider only. For a new agent, if the developer names Anthropic or Google, say that this
-release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic
-and Google come in a later release, and offer the built-in CopilotKit agent if they need
-Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on
-Anthropic or Google, add one line to the plan: the page context that CopilotKit sends can
-fail with that vendor until a CopilotKit SDK release fixes it (PE-728). Take that vendor's
+vendor. OpenAI, an OpenAI-compatible provider, Anthropic, and Google work. An existing agent keeps its vendor and model. Take that vendor's
 package, class, and credential variable names from the framework's own documentation, and
 use a model id that the vendor serves to a new key today. For an OpenAI-compatible
 provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and
@@ -37,7 +31,7 @@ Record the selected framework, vendor, model, required credential variable names
 these URLs.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/langgraph-typescript.md

@@ -1,19 +1,13 @@
 # Configure LangGraph TypeScript
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing LangGraph TypeScript model setup. For a new agent, use the vendor
 that the framework step recorded. Use OpenAI only when the record and this conversation
-have no vendor. This release offers a new agent on this framework OpenAI or an
-OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or
-Google, say that this release supports OpenAI or an OpenAI-compatible provider on this
-framework, that Anthropic and Google come in a later release, and offer the built-in
-CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor
-and model. If it runs on Anthropic or Google, add one line to the plan: the page context
-that CopilotKit sends can fail with that vendor until a CopilotKit SDK release fixes it
-(PE-728). Take that vendor's package, class, and credential variable names from the
+have no vendor. OpenAI, an OpenAI-compatible provider, Anthropic, and Google work. An existing agent keeps its vendor
+and model. Take that vendor's package, class, and credential variable names from the
 framework's own documentation, and use a model id that the vendor serves to a new key
 today. For an OpenAI-compatible provider, keep `OPENAI_API_KEY`, use the model id that
 `setup/questions` recorded, and write the base URL that `setup/questions` recorded as
@@ -42,7 +36,7 @@ Record the selected framework, vendor, model, required credential variable names
 start command, and these URLs.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/llamaindex.md

@@ -1,18 +1,12 @@
 # Configure LlamaIndex
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing LlamaIndex model setup. For a new agent, use the vendor that the
 framework step recorded. Use OpenAI only when the record and this conversation have no
-vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible
-provider only. For a new agent, if the developer names Anthropic or Google, say that this
-release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic
-and Google come in a later release, and offer the built-in CopilotKit agent if they need
-Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on
-Anthropic or Google, add one line to the plan: the page context that CopilotKit sends can
-fail with that vendor until a CopilotKit SDK release fixes it (PE-728). Take that vendor's
+vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or Google, say that this release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic and Google come in a later release, and offer the built-in CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on Anthropic or Google, add one line to the plan: this CopilotKit CLI release has not proven Anthropic or Google on this framework, so a chat can fail with it. Take that vendor's
 package, class, and credential variable names from the framework's own documentation, and
 use a model id that the vendor serves to a new key today. For an OpenAI-compatible
 provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and
@@ -51,7 +45,7 @@ Record the selected framework, vendor, model, required credential variable names
 URLs, the documented dependencies and adapter, and both documentation limits.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/mastra.md

@@ -1,18 +1,12 @@
 # Configure Mastra
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing Mastra model setup. For a new agent, use the vendor that the
 framework step recorded. Use OpenAI only when the record and this conversation have no
-vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible
-provider only. For a new agent, if the developer names Anthropic or Google, say that this
-release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic
-and Google come in a later release, and offer the built-in CopilotKit agent if they need
-Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on
-Anthropic or Google, add one line to the plan: the page context that CopilotKit sends can
-fail with that vendor until a CopilotKit SDK release fixes it (PE-728). Take that vendor's
+vendor. OpenAI, an OpenAI-compatible provider, Anthropic, and Google work. An existing agent keeps its vendor and model. Take that vendor's
 package, class, and credential variable names from the framework's own documentation, and
 use a model id that the vendor serves to a new key today. For an OpenAI-compatible
 provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and
@@ -63,7 +57,7 @@ Record the selected framework, vendor, model, required credential variable names
 these URLs.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/ms-agent-dotnet.md

@@ -1,19 +1,12 @@
 # Configure Microsoft Agent Framework for .NET
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing Microsoft Agent Framework model setup. For a new agent, use the
 vendor that the framework step recorded. Use direct OpenAI only when the record and this
-conversation have no vendor, and name its credential `OPENAI_API_KEY`. This release offers
-a new agent on this framework OpenAI or an OpenAI-compatible provider only. For a new
-agent, if the developer names Anthropic or Google, say that this release supports OpenAI
-or an OpenAI-compatible provider on this framework, that Anthropic and Google come in a
-later release, and offer the built-in CopilotKit agent if they need Anthropic or Google
-now. An existing agent keeps its vendor and model. If it runs on Anthropic or Google, add
-one line to the plan: the page context that CopilotKit sends can fail with that vendor
-until a CopilotKit SDK release fixes it (PE-728). Take that vendor's package, class, and
+conversation have no vendor, and name its credential `OPENAI_API_KEY`. This release offers a new agent on this framework OpenAI or an OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or Google, say that this release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic and Google come in a later release, and offer the built-in CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on Anthropic or Google, add one line to the plan: this CopilotKit CLI release has not proven Anthropic or Google on this framework, so a chat can fail with it. Take that vendor's package, class, and
 credential variable names from the framework's own documentation, and use a model id that
 the vendor serves to a new key today. For an OpenAI-compatible provider, keep
 `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and write the base URL
@@ -33,13 +26,13 @@ Run `dotnet --version` before you change the project. If it fails, no .NET SDK i
 shell's PATH. Do not change the project, and do not install the SDK yourself. Tell the
 developer to install the .NET SDK from https://dotnet.microsoft.com/download. Say that the
 coding agent's shell cannot see a new install until the developer restarts the coding
-agent. Give them `npx --prefer-offline --yes copilotkit@4.29.0 onboard start --run <onboarding_run_id>`
+agent. Give them `npx --prefer-offline --yes copilotkit@4.30.0 onboard start --run <onboarding_run_id>`
 to resume the run after the restart.
 
 Before you end your turn to wait for the developer, report the pause:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about environment-fix
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about environment-fix
 ```
 
 Then end your turn and wait for the developer.
@@ -67,7 +60,7 @@ Record the selected framework, provider, model, required credential variable nam
 these URLs.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/ms-agent-harness-dotnet.md

@@ -1,20 +1,14 @@
 # Configure MS Agent Harness for .NET
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing MS Agent Harness model, provider, credential name, and host setup.
 For a new setup, use the vendor that the framework step recorded. Use direct OpenAI only
 when the record and this conversation have no vendor, and name its credential
-`OPENAI_API_KEY`. This release offers a new agent on this framework OpenAI or an
-OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or
-Google, say that this release supports OpenAI or an OpenAI-compatible provider on this
-framework, that Anthropic and Google come in a later release, and offer the built-in
-CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor
-and model. If it runs on Anthropic or Google, add one line to the plan: the page context
-that CopilotKit sends can fail with that vendor until a CopilotKit SDK release fixes it
-(PE-728). Take that vendor's package, class, and credential variable names from the
+`OPENAI_API_KEY`. This release offers a new agent on this framework OpenAI or an OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or Google, say that this release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic and Google come in a later release, and offer the built-in CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor
+and model. If it runs on Anthropic or Google, add one line to the plan: this CopilotKit CLI release has not proven Anthropic or Google on this framework, so a chat can fail with it. Take that vendor's package, class, and credential variable names from the
 framework's own documentation, and use a model id that the vendor serves to a new key
 today. For an OpenAI-compatible provider, keep `OPENAI_API_KEY`, use the model id that
 `setup/questions` recorded, and write the base URL that `setup/questions` recorded as
@@ -28,13 +22,13 @@ you change the project. If it fails, no .NET SDK is on this shell's PATH. Do not
 the project, and do not install the SDK yourself. Tell the developer to install the .NET
 SDK from https://dotnet.microsoft.com/download. Say that the coding agent's shell cannot
 see a new install until the developer restarts the coding agent. Give them
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard start --run <onboarding_run_id>` to resume the run
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard start --run <onboarding_run_id>` to resume the run
 after the restart.
 
 Before you end your turn to wait for the developer, report the pause:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about environment-fix
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about environment-fix
 ```
 
 Then end your turn and wait for the developer.
@@ -76,7 +70,7 @@ Record the selected framework, provider, model, required credential variable nam
 URLs, and the quickstart gap.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/ms-agent-python.md

@@ -1,19 +1,13 @@
 # Configure Microsoft Agent Framework for Python
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing Microsoft Agent Framework model setup. For a new agent, use the
 vendor that the framework step recorded. Use OpenAI only when the record and this
-conversation have no vendor. This release offers a new agent on this framework OpenAI or
-an OpenAI-compatible provider only. For a new agent, if the developer names Anthropic or
-Google, say that this release supports OpenAI or an OpenAI-compatible provider on this
-framework, that Anthropic and Google come in a later release, and offer the built-in
-CopilotKit agent if they need Anthropic or Google now. An existing agent keeps its vendor
-and model. If it runs on Anthropic or Google, add one line to the plan: the page context
-that CopilotKit sends can fail with that vendor until a CopilotKit SDK release fixes it
-(PE-728). Take that vendor's package, class, and credential variable names from the
+conversation have no vendor. This release offers a new agent on this framework OpenAI, an OpenAI-compatible provider, or Anthropic only. For a new agent, if the developer names Google, say that this release supports OpenAI, an OpenAI-compatible provider, or Anthropic on this framework, that Google comes in a later release, and offer the built-in CopilotKit agent if they need Google now. An existing agent keeps its vendor
+and model. If it runs on Google, add one line to the plan: this CopilotKit CLI release has not proven Google on this framework, so a chat can fail with it. Take that vendor's package, class, and credential variable names from the
 framework's own documentation, and use a model id that the vendor serves to a new key
 today. For an OpenAI-compatible provider, keep `OPENAI_API_KEY`, use the model id that
 `setup/questions` recorded, and write the base URL that `setup/questions` recorded as
@@ -47,7 +41,7 @@ Record the selected framework, vendor, model, required credential variable names
 these URLs.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/pydantic-ai.md

@@ -1,18 +1,12 @@
 # Configure Pydantic AI
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing Pydantic AI model setup. For a new agent, use the vendor that the
 framework step recorded. Use OpenAI only when the record and this conversation have no
-vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible
-provider only. For a new agent, if the developer names Anthropic or Google, say that this
-release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic
-and Google come in a later release, and offer the built-in CopilotKit agent if they need
-Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on
-Anthropic or Google, add one line to the plan: the page context that CopilotKit sends can
-fail with that vendor until a CopilotKit SDK release fixes it (PE-728). Take that vendor's
+vendor. OpenAI, an OpenAI-compatible provider, Anthropic, and Google work. An existing agent keeps its vendor and model. Take that vendor's
 package, class, and credential variable names from the framework's own documentation, and
 use a model id that the vendor serves to a new key today. For an OpenAI-compatible
 provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and
@@ -59,7 +53,7 @@ Record the selected framework, vendor, model, required credential variable names
 URLs, and the two-step context route.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/strands-python.md

@@ -1,18 +1,12 @@
 # Configure Strands Agents Python
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing Strands model setup. For a new agent, use the vendor that the
 framework step recorded. Use OpenAI only when the record and this conversation have no
-vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible
-provider only. For a new agent, if the developer names Anthropic or Google, say that this
-release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic
-and Google come in a later release, and offer the built-in CopilotKit agent if they need
-Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on
-Anthropic or Google, add one line to the plan: the page context that CopilotKit sends can
-fail with that vendor until a CopilotKit SDK release fixes it (PE-728). Take that vendor's
+vendor. This release offers a new agent on this framework OpenAI, an OpenAI-compatible provider, or Anthropic only. For a new agent, if the developer names Google, say that this release supports OpenAI, an OpenAI-compatible provider, or Anthropic on this framework, that Google comes in a later release, and offer the built-in CopilotKit agent if they need Google now. An existing agent keeps its vendor and model. If it runs on Google, add one line to the plan: this CopilotKit CLI release has not proven Google on this framework, so a chat can fail with it. Take that vendor's
 package, class, and credential variable names from the framework's own documentation, and
 use a model id that the vendor serves to a new key today. For an OpenAI-compatible
 provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and
@@ -48,7 +42,7 @@ Record the selected framework, vendor, model, required credential variable names
 URLs, and how the agent reads `context`.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/framework/strands-typescript.md

@@ -1,18 +1,12 @@
 # Configure Strands Agents TypeScript
 
-First run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers`. Its `vendor` is the
+First run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers`. Its `vendor` is the
 vendor the framework step recorded, even after this conversation lost it, with
 `vendor.baseUrl` and `vendor.modelId` for an OpenAI-compatible provider.
 
 Preserve an existing Strands model setup. For a new agent, use the vendor that the
 framework step recorded. Use OpenAI only when the record and this conversation have no
-vendor. This release offers a new agent on this framework OpenAI or an OpenAI-compatible
-provider only. For a new agent, if the developer names Anthropic or Google, say that this
-release supports OpenAI or an OpenAI-compatible provider on this framework, that Anthropic
-and Google come in a later release, and offer the built-in CopilotKit agent if they need
-Anthropic or Google now. An existing agent keeps its vendor and model. If it runs on
-Anthropic or Google, add one line to the plan: the page context that CopilotKit sends can
-fail with that vendor until a CopilotKit SDK release fixes it (PE-728). Take that vendor's
+vendor. This release offers a new agent on this framework OpenAI, an OpenAI-compatible provider, or Anthropic only. For a new agent, if the developer names Google, say that this release supports OpenAI, an OpenAI-compatible provider, or Anthropic on this framework, that Google comes in a later release, and offer the built-in CopilotKit agent if they need Google now. An existing agent keeps its vendor and model. If it runs on Google, add one line to the plan: this CopilotKit CLI release has not proven Google on this framework, so a chat can fail with it. Take that vendor's
 package, class, and credential variable names from the framework's own documentation, and
 use a model id that the vendor serves to a new key today. For an OpenAI-compatible
 provider, keep `OPENAI_API_KEY`, use the model id that `setup/questions` recorded, and
@@ -49,7 +43,7 @@ Record the selected framework, vendor, model, required credential variable names
 URLs, and how the agent reads `context`.
 
 If the pages support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/angular.md

@@ -6,13 +6,13 @@ This step asks the developer nothing. If the run must wait for the developer any
 the pause first:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about other
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about other
 ```
 
 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 --prefer-offline --yes copilotkit@4.29.0 onboard read starter/clone` before you fetch documentation.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read starter/clone` before you fetch documentation.
 
 ## Documentation
 
@@ -59,7 +59,7 @@ 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 --prefer-offline --yes copilotkit@4.29.0 onboard read credentials/finalize-plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, or the two version lines do not fit
-together, run `npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+together, run `npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/nextjs.md

@@ -6,7 +6,7 @@ This step asks the developer nothing. If the run must wait for the developer any
 the pause first:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about other
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about other
 ```
 
 Use the starter shortcut only if the target directory holds no project and its name is
@@ -22,7 +22,7 @@ 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 --prefer-offline --yes copilotkit@4.29.0 onboard read starter/clone` before you fetch documentation.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read starter/clone` before you fetch documentation.
 
 ## Documentation
 
@@ -73,7 +73,7 @@ also sets `outputFileTracingRoot`. Do not set `outputFileTracingRoot` to a
 different folder. For an existing frontend, name this change in the report.
 
 If the page supports the selection, record Next.js and this URL. Then run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read credentials/finalize-plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/plan.md

@@ -15,18 +15,18 @@ Every rule below is for a run that named neither.
 
 ## Use the recorded frontend
 
-Run `npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers` and use its `frontend`. It holds
+Run `npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers` and use its `frontend`. It holds
 the answer that `setup/questions` recorded, even after this conversation lost it. If the
 project has a frontend, preserve it and use the matching route below. Do not change
 application code in this phase. If neither settles it, ask one line as the options view
 of `onboard setup-message` does: the recommendation first, in bold, and the alternatives on one `Other:` line, from
 React SPA, Next.js, Angular, Vue 3, React Native, Slack, and Microsoft Teams. Record the answer with
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard setup-answers --frontend <name>`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard setup-answers --frontend <name>`.
 
 Before you end your turn to wait for the developer, report the pause:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about stack-choice
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about stack-choice
 ```
 
 When the recorded frontend is not Next.js, tell the developer in one sentence where it runs
@@ -38,15 +38,15 @@ words instead.
 
 Use exactly one matching internal route:
 
-1. React SPA: `npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/react-spa`
-2. Next.js: `npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/nextjs`
-3. Angular: `npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/angular`
-4. Vue 3: `npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/vue`
-5. React Native: `npx --prefer-offline --yes copilotkit@4.29.0 onboard read frontend/react-native`
-6. Slack or Microsoft Teams: `npx --prefer-offline --yes copilotkit@4.29.0 onboard read feature/channels/start`
+1. React SPA: `npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/react-spa`
+2. Next.js: `npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/nextjs`
+3. Angular: `npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/angular`
+4. Vue 3: `npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/vue`
+5. React Native: `npx --prefer-offline --yes copilotkit@4.30.0 onboard read frontend/react-native`
+6. Slack or Microsoft Teams: `npx --prefer-offline --yes copilotkit@4.30.0 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 --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

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

@@ -6,7 +6,7 @@ This step asks the developer nothing. If the run must wait for the developer any
 the pause first:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about other
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about other
 ```
 
 React Native has no starter. For a target directory that holds no project, build the new
@@ -25,7 +25,7 @@ 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 --prefer-offline --yes copilotkit@4.29.0 onboard read credentials/finalize-plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

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

@@ -6,7 +6,7 @@ This step asks the developer nothing. If the run must wait for the developer any
 the pause first:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about other
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about other
 ```
 
 React SPA has no starter. For a target directory that holds no project, build the new
@@ -26,7 +26,7 @@ that import when Vite leaves the package external.
 - https://docs.copilotkit.ai/react-spa.md
 
 If the page supports the selection, record React SPA and this URL. Then run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read credentials/finalize-plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/frontend/vue.md

@@ -6,7 +6,7 @@ This step asks the developer nothing. If the run must wait for the developer any
 the pause first:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-developer --about other
+npx --prefer-offline --yes copilotkit@4.30.0 onboard checkpoint --phase awaiting-developer --about other
 ```
 
 Vue 3 has no starter. For a target directory that holds no project, build the new
@@ -26,7 +26,7 @@ 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 --prefer-offline --yes copilotkit@4.29.0 onboard read credentials/finalize-plan`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read credentials/finalize-plan`.
 
 If the documentation does not support the selection, run
-`npx --prefer-offline --yes copilotkit@4.29.0 onboard read unsupported/no-validated-path`.
+`npx --prefer-offline --yes copilotkit@4.30.0 onboard read unsupported/no-validated-path`.