Migrate the copilotkit CLI (npx copilotkit create/init/dev) from
CopilotCloud into packages/v1/cli. TEMPLATE_REPOS updated to use
monorepo subdirectory sparse checkout for all CopilotKit-owned
templates, with tarball fallback for external repos (ag2).
Replace Zod-specific types (z.ZodType, z.infer) with Standard Schema V1
interfaces across the V2 public API surface. This allows users to use any
Standard Schema V1 compatible library (Zod 3.24+, Valibot v1+, ArkType v2+)
for tool parameters, with zero breaking changes for existing Zod users.
- Add schemaToJsonSchema() utility in shared with Standard JSON Schema V1
support and Zod fallback
- Update FrontendTool, ToolDefinition, useRenderTool, useComponent, and
Angular tool types to accept StandardSchemaV1
- Move zod from dependencies to devDependencies in core and angular
- Add runtime tests (40) and type-level tests (38) across all packages
verifying Zod, Valibot, and ArkType compatibility
The lockfile was out of sync with packages/v2/agent/package.json after
the @copilotkitnext/shared workspace dependency was added, causing all
CI workflows to fail at the install step.
## Summary
- `@copilotkit/runtime-client-gql` declared `@copilotkit/runtime` as a
dependency, but never imports from it at runtime
- This caused barrel re-exports to pull server-side code into client
bundles (600KB → 4.3MB)
- Removed the package.json dependency and added an Nx
`implicitDependencies` entry to preserve build ordering (graphql-codegen
needs the schema file that runtime generates)
Fixes#3225
## Test plan
- [x] Verified no source imports from `@copilotkit/runtime` in
runtime-client-gql
- [x] Nx build ordering preserved via `implicitDependencies`
- [x] Full build passes (including graphql-codegen)
- [x] All tests pass
🤖 Generated with [Claude Code](https://claude.ai/code)
The @copilotkit/runtime-client-gql package listed @copilotkit/runtime as
a dependency, but none of its source files actually import from it. This
caused the entire server-side runtime (graphql-yoga, hono, openai, shiki,
reflect-metadata, etc.) to be pulled into client bundles, exploding
bundle size from ~600kb to 4.3mb+.
Remove the unused dependency from package.json, the UMD externals list,
and the UMD globals map in tsdown.config.ts.
Fixes#2903
## The Bug
Azure OpenAI users get `AI_LoadAPIKeyError: OpenAI API key is missing`
despite passing a properly configured `OpenAI` instance to
`OpenAIAdapter`, exactly as shown in the docs.
**Root cause**: `CopilotRuntime.handleServiceAdapter()` discards the
adapter's configured OpenAI instance and constructs a plain string
`"openai/gpt-4o"` to pass to `BuiltInAgent`. The agent's
`resolveModel()` then creates a *brand new* OpenAI provider using only
`OPENAI_API_KEY`, losing all Azure configuration (baseURL, api-key
header, api-version query param).
The V1 adapter's `process()` method — which correctly uses the custom
OpenAI instance — is dead code. It's never called. Only `.provider` and
`.model` strings are extracted.
```
User configures Azure OpenAI instance →
OpenAIAdapter stores it →
CopilotRuntime extracts only "openai"/"gpt-4o" strings →
BuiltInAgent.resolveModel("openai/gpt-4o") →
createOpenAI({ apiKey: OPENAI_API_KEY }) →
💥 API key missing / wrong endpoint
```
## Workaround
Until this is merged, users can bypass the broken adapter entirely by
using `BuiltInAgent` directly with the Vercel AI SDK Azure provider:
```typescript
import { createAzure } from "@ai-sdk/azure";
import { CopilotRuntime, copilotRuntimeNodeHttpEndpoint } from "@copilotkit/runtime";
import { BuiltInAgent } from "@copilotkitnext/agent";
const azure = createAzure({
resourceName: process.env.AZURE_RESOURCE_NAME,
apiKey: process.env.AZURE_API_KEY,
});
const runtime = new CopilotRuntime({
agents: {
default: new BuiltInAgent({
model: azure("your-deployment-name"),
}),
},
});
// Then use copilotRuntimeNodeHttpEndpoint as usual — no serviceAdapter needed
```
This works because `BuiltInAgent` already accepts `LanguageModel`
instances and `resolveModel()` passes them straight through.
## The Fix
Add an optional `getLanguageModel()` method to `CopilotServiceAdapter`.
Adapters that accept custom SDK instances (OpenAI, Anthropic, Groq) now
implement this to produce a pre-configured Vercel AI SDK `LanguageModel`
that carries the full provider configuration. `CopilotRuntime` prefers
this over the string format when creating `BuiltInAgent`.
**Backward compatible**: `getLanguageModel()` is optional on the
interface, so existing custom adapters continue to work unchanged.
| File | Change |
|------|--------|
| `service-adapter.ts` | Add optional `getLanguageModel()` to
`CopilotServiceAdapter` interface |
| `openai-adapter.ts` | Implement `getLanguageModel()` using
`createOpenAI` with the configured instance's `baseURL`/`apiKey` |
| `anthropic-adapter.ts` | Implement `getLanguageModel()` using
`createAnthropic` |
| `groq-adapter.ts` | Implement `getLanguageModel()` using
`createOpenAI` (Groq is OpenAI-compatible) |
| `copilot-runtime.ts` | Prefer `serviceAdapter.getLanguageModel()` over
string model when creating `BuiltInAgent` |
| `package.json` | Add `ai`, `@ai-sdk/openai`, `@ai-sdk/anthropic`
dependencies |
## Test plan
- [x] V2 agent tests pass (101/101)
- [x] V1 runtime build succeeds with no type errors
- [x] V1 runtime tests: same pass/fail as `main` (pre-existing failures
unrelated to this change)
- [ ] Manual: configure Azure OpenAI via `OpenAIAdapter` without
`OPENAI_API_KEY` — should work without `AI_LoadAPIKeyError`
- [ ] Manual: standard OpenAI via `OpenAIAdapter` with `OPENAI_API_KEY`
— should continue working
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Service adapters (OpenAIAdapter, AnthropicAdapter, GroqAdapter) accept
custom SDK instances with provider-specific configuration (e.g. Azure
OpenAI with custom baseURL/apiKey/headers), but CopilotRuntime discards
those instances and reconstructs a plain "provider/model" string for
BuiltInAgent. The agent's resolveModel() then creates a fresh provider
using only environment variables, losing all custom configuration.
Add getLanguageModel() to CopilotServiceAdapter so adapters can produce
a pre-configured Vercel AI SDK LanguageModel. CopilotRuntime now prefers
this over the string format when creating BuiltInAgent.
FixesCopilotKit/CopilotKit#2903
- Replace husky with lefthook for git hooks management
- Pre-commit runs lint --fix, format, test, and check:packages in parallel
with auto-staging of fixes via stage_fixed
- Commit-msg runs commitlint
- Add dependsOn ^build to test target in nx.json so dependencies are
built before tests run
- Upgrade @analogjs/vite-plugin-angular and @analogjs/vitest-angular
from ^1.20.2 to ^2.2.3 for vite 7 compatibility
- Add pnpm packageExtensions to declare missing vite peer dependency
on @analogjs/vite-plugin-angular
- Fix lint issues: let -> const in agent and react packages
- Disable nx TUI in pre-commit hooks via NX_TUI env var
Max Korp