copilotkit 4.9.37 → 4.9.50

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@4.9.37 onboard read subagent/prove-round-trip` first and follow the
+`npx --yes copilotkit@4.9.50 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
@@ -23,13 +23,13 @@ pass the time.
 Report each attempt at the journey as it ends, counting from one:
 
 ```text
-npx --yes copilotkit@4.9.37 onboard checkpoint --phase journey-attempted --attempt 1
+npx --yes copilotkit@4.9.50 onboard checkpoint --phase journey-attempted --attempt 1
 ```
 
 Record what that proof returned before you route on it:
 
 ```text
-npx --yes copilotkit@4.9.37 onboard proof --step round-trip --outcome <passed|failed|skipped>
+npx --yes copilotkit@4.9.50 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
@@ -37,7 +37,7 @@ 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@4.9.37 onboard audit` from the target app directory. If its result
+`npx --yes copilotkit@4.9.50 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
@@ -46,13 +46,13 @@ 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@4.9.37 onboard protect --accept-external --path <path>`. Then run
+`npx --yes copilotkit@4.9.50 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.
 
 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@4.9.37 onboard read proof/complete`. A performed surface outcome with
+`npx --yes copilotkit@4.9.50 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
@@ -108,7 +108,7 @@ Restart each project-owned process changed by the repair. Report the cycle, coun
 one:
 
 ```text
-npx --yes copilotkit@4.9.37 onboard checkpoint --phase repair-attempted --attempt 1
+npx --yes copilotkit@4.9.50 onboard checkpoint --phase repair-attempted --attempt 1
 ```
 
 Then spawn a fresh proof subagent
@@ -126,7 +126,7 @@ 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@4.9.37 onboard read unsupported/no-validated-path`. All three are
+`npx --yes copilotkit@4.9.50 onboard read unsupported/no-validated-path`. All three are
 about the round trip itself. A round trip that proved is not one of them, whatever failed
 after it.
 
@@ -136,7 +136,7 @@ Run the feedback command without another developer question. The CLI telemetry g
 whether the report is sent.
 
 ```text
-npx --yes copilotkit@4.9.37 onboard feedback
+npx --yes copilotkit@4.9.50 onboard feedback
 ```
 
 Write at most four lines to standard input: the step you stopped at and what stopped it.

package/onboarding/prompts/starter/clone.md

@@ -43,7 +43,7 @@ the derived name.
 Only if the developer asks for an existing project, or asks to see the projects they have,
 read the choices:
 
-`npx --yes copilotkit@4.9.37 project list --json`
+`npx --yes copilotkit@4.9.50 project list --json`
 
 Then ask which one to use. Do not order the projects by creation time. If the developer
 already gave this answer, do not ask again. Do not read a secret value. Do not show or
@@ -53,7 +53,7 @@ Run the command from the parent directory. Do not inspect another entry in the p
 directory. Replace each placeholder with the recorded value. Do not run a placeholder as
 a shell argument.
 
-`npx --yes copilotkit@4.9.37 init --name <project-name> --framework <framework-id> --channel none --no-banner --create <name> --install`
+`npx --yes copilotkit@4.9.50 init --name <project-name> --framework <framework-id> --channel none --no-banner --create <name> --install`
 
 Pass the confirmed name to both `--name` and `--create`: the app directory and its
 Intelligence project take the same name here. If the developer names an existing project,
@@ -69,14 +69,14 @@ account. The command does not need terminal input.
 If the command succeeds, do not rebuild the starter by hand. Report the clone first:
 
 ```text
-npx --yes copilotkit@4.9.37 onboard checkpoint --phase starter-cloned
+npx --yes copilotkit@4.9.50 onboard checkpoint --phase starter-cloned
 ```
 
 Then inspect only the generated
 paths inside the target directory. Record the files, install result, project connection,
 and validation commands. Then run
-`npx --yes copilotkit@4.9.37 onboard read proof/round-trip`.
+`npx --yes copilotkit@4.9.50 onboard read proof/round-trip`.
 
 If the command fails, report its exact error and do not claim that the starter is ready.
 Then run
-`npx --yes copilotkit@4.9.37 onboard read unsupported/no-validated-path`.
+`npx --yes copilotkit@4.9.50 onboard read unsupported/no-validated-path`.

package/onboarding/prompts/subagent/create-plan.md

@@ -122,7 +122,7 @@ here is work the developer did not ask for.
 Plan the threads drawer itself: add it from the selected drawer page, where this frontend
 does not already render one. Where this journey's frontend framework ships no threads
 drawer -- React Native --, plan that the thread is proved by
-`npx --yes copilotkit@4.9.37 verify --round-trip`, which needs no browser. Do not plan a
+`npx --yes copilotkit@4.9.50 verify --round-trip`, which needs no browser. Do not plan a
 step that opens the managed Intelligence dashboard.
 
 ## Order the plan into steps
@@ -138,8 +138,16 @@ list to re-derive: a path you leave out of it is not protected, and a path you a
 is not in the baseline the audit reads. Do not name a protected path as a path a step
 changes. Do not name a path that overlaps a protected path. The paths overlap when they are
 equal or either path is an ancestor directory on a path-segment boundary. `apps/a` overlaps
-`apps/a/src`, but not `apps/ab`. `app.ts` does not overlap `app.tsx`. If the plan needs
-one, return `Status: blocked` before approval.
+`apps/a/src`, but not `apps/ab`. `app.ts` does not overlap `app.tsx`.
+
+If a step cannot be written any other way, ask for the path instead of taking it. Adding a
+feature to an app the developer already built is the case this exists for: the option lives
+in a file they wrote, and on an app whose work was never committed that file is in the
+baseline. List every such path under `Authorization requested`, one line each, with the path
+and one sentence saying what the step changes there and why no other file will do. Keep the
+step in the plan. Return `Status: blocked` only when the plan needs a protected path you
+cannot justify in that sentence.
+
 Return the protected path list as part of the plan.
 
 Keep final validation and proof outside the implementation steps. The developer approves

package/onboarding/prompts/subagent/prove-oss-baseline.md

@@ -19,7 +19,7 @@ Prove the live runtime in this order:
 4. Confirm from project files that the runtime constructor passes a `runner` option rather
    than an `intelligence` option. A package, import, project file, or key is not use proof.
 5. Run
-   `npx --yes copilotkit@4.9.37 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
+   `npx --yes copilotkit@4.9.50 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
    with the runtime URL or auth header options that this project needs. Require exit zero
    and the JSON `ok` field to be `true`.
 6. Drive one real request through the existing frontend, CopilotKit runtime, and expected

package/onboarding/prompts/subagent/prove-round-trip.md

@@ -90,8 +90,11 @@ A server that never answered has written the reason to its own output, and readi
 output is faster than starting it again.
 
 Leave the agent and frontend servers running after proof. Record each process ID and a
-safe command that stops that process. Record the frontend URL, written with `localhost`
-rather than an IP literal, and the commands that start both servers again.
+safe command that stops that process. Record the commands that start both servers again.
+
+Record the frontend URL the server you started reports, and treat it as provisional. Step 4
+replaces it with the URL the CLI resolves. Do not compose one of your own from a port you
+read here.
 
 ## Step 3 -- Identify the process that answered
 
@@ -120,7 +123,7 @@ IPv6 only, so an IPv4 literal fails against the correct port.
 ## Step 4 -- Check the wiring
 
 With both running, check the wiring in one command before you open a browser:
-`npx --yes copilotkit@4.9.37 verify --json`. It reads the port from this project, so a
+`npx --yes copilotkit@4.9.50 verify --json`. It reads the port from this project, so a
 non-default port needs no flag. The payload reports `runtimeUrl` and `runtimeUrlSource`. A
 `runtimeUrlSource` of `default` means nothing in the project named a port, so pass
 `--runtime-url` with the URL from step 1 in that case. Read the individual checks rather than
@@ -135,7 +138,7 @@ used the Intelligence credential. `api_key_authenticates` proves only that the k
 will not read. `verify` searches upward for the credential and a framework's env loader
 does not, so a key at the repository root is invisible to an app in a subdirectory. The
 check names the file to write instead. Write the key there, or run
-`npx --yes copilotkit@4.9.37 project select` from the app directory. Do not link,
+`npx --yes copilotkit@4.9.50 project select` from the app directory. Do not link,
 copy, or symlink the file to work around it, and do not treat the credential as missing:
 the check above already reported that it exists.
 
@@ -144,9 +147,21 @@ mounted `mode: "single-route"` is the usual cause. Return it for implementation
 option and use a catch-all route. Do not edit it. If the check is `undetermined` because no
 thread-endpoint state exists, the runtime predates the field. Record that and continue.
 
+Take the frontend URL from the payload's `frontendUrl`. It replaces whatever step 2
+recorded, and every later step uses it unchanged. Where the field is absent, the project
+named no port the CLI can read: keep step 2's URL, and rewrite its host as `localhost`
+before you use it.
+
+Then run the command once more with the URL you are about to open:
+`npx --yes copilotkit@4.9.50 verify --frontend-url <that url> --json`. The
+`frontend_assets_served` check asks that server for its page and for one of the page's own
+assets, on that exact host. A `fail` there means the dev server refuses its own static
+assets on the host you were about to use, and the check names the URL to use instead. This
+is the cheapest step that can save the most expensive one, so run it before the browser.
+
 ## Step 5 -- Prove that the agent runs
 
-Run `npx --yes copilotkit@4.9.37 verify --round-trip --json`. It sends one request through
+Run `npx --yes copilotkit@4.9.50 verify --round-trip --json`. It sends one request through
 the runtime and reads the answer back from the thread, so it separates an agent that is
 configured from an agent that works. Use `--agent <id>` when the runtime declares more
 than one. If it reports `user-not-identified`, this project's `identifyUser` reads a
@@ -223,7 +238,7 @@ For a recorded `both-oss` starting state, this step has no component to render.
 same request the baseline recorded, require the same kind of user-visible result the
 baseline produced, and require that the thread for that request is listed in the drawer.
 Where this journey's frontend framework ships no threads drawer -- React Native --, prove
-that thread with `npx --yes copilotkit@4.9.37 verify --round-trip`, which reads the
+that thread with `npx --yes copilotkit@4.9.50 verify --round-trip`, which reads the
 answer back off the thread and needs no browser. Record which of the two you proved.
 
 Use the surface control the main coding agent recorded for your environment. It either had
@@ -247,11 +262,14 @@ under a name that says what it was.
 The surface is a browser, and it also covers browser-origin CORS and CSP, which a CLI
 request never exercises. Drive it with the browser control step 6 named.
 
-1. Open the frontend URL from step 2 and wait for the page to finish loading.
-   Address it as `localhost` rather than an IP literal, for the reason step 3 gives
-   for the agent. A dev server reached on the IP literal can refuse its own static
-   assets, and a page that loads without them leaves the chat control dead. That
-   reads as a broken integration rather than as the host name you used.
+1. Open the frontend URL step 4 resolved, exactly as that step recorded it, and wait for
+   the page to finish loading. Do not retype the host, and do not substitute a URL a tool
+   offers you by default. Where the page loads but its styling is missing or the chat
+   control is dead, run
+   `npx --yes copilotkit@4.9.50 verify --frontend-url <the url you opened> --json`
+   before you diagnose anything else. A dev server can serve its page and refuse every
+   static chunk behind it, and on screen that is indistinguishable from a broken
+   integration. The `frontend_assets_served` check tells the two apart.
 2. Take one page snapshot. Record whether the CopilotKit surface is on the page. A page
    that renders without it is a wiring failure rather than a proof to retry.
 3. Read the browser console before you type anything, and record every error already

package/onboarding/prompts/unsupported/no-validated-path.md

@@ -30,13 +30,13 @@ Before you show the best-effort plan, require this complete packet:
 - Give the ordered proof rules.
 
 After the developer approves the best-effort plan, run
-`npx --yes copilotkit@4.9.37 onboard read fallback/best-effort`.
+`npx --yes copilotkit@4.9.50 onboard read fallback/best-effort`.
 
 Send one short report. Run the feedback command without another developer question. The
 CLI telemetry gate decides whether the report is sent.
 
 ```text
-npx --yes copilotkit@4.9.37 onboard feedback
+npx --yes copilotkit@4.9.50 onboard feedback
 ```
 
 Write the feedback message to the command's standard input, in at most four lines.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "copilotkit",
-  "version": "4.9.37",
+  "version": "4.9.50",
   "type": "module",
   "repository": {
     "type": "git",

package/release/release-tool.js

@@ -14698,7 +14698,7 @@ import * as path4 from "node:path";
 
 // apps/cli/src/config.ts
 function getTemplateRef() {
-  return true ? "aec312634129f97f90154bb416a07e8cc0c13a2a" : "main";
+  return true ? "380ad1220a7bc78104baedc469c4d086c8910494" : "main";
 }
 
 // apps/cli/src/services/agentcore-config.ts
@@ -14896,8 +14896,15 @@ var TELEMETRY_ERROR_CODES = {
    */
   KEY_PROVISION_REFUSED: "KEY_PROVISION_REFUSED",
   CLI_PRODUCT_BINARY_TOO_LARGE: "CLI_PRODUCT_BINARY_TOO_LARGE",
+  LEARNING_CANDIDATE_CONFLICT: "LEARNING_CANDIDATE_CONFLICT",
+  LEARNING_CANDIDATE_SETTLED: "LEARNING_CANDIDATE_SETTLED",
+  LEARNING_CANDIDATE_ID_INVALID: "LEARNING_CANDIDATE_ID_INVALID",
   LEARNING_CONTAINER_ID_INVALID: "LEARNING_CONTAINER_ID_INVALID",
+  LEARNING_CONTAINER_INPUT_INVALID: "LEARNING_CONTAINER_INPUT_INVALID",
+  LEARNING_CONTAINER_NOT_FOUND: "LEARNING_CONTAINER_NOT_FOUND",
+  LEARNING_CONTAINER_RESPONSE_INVALID: "LEARNING_CONTAINER_RESPONSE_INVALID",
   LEARNING_PROJECT_ID_INVALID: "LEARNING_PROJECT_ID_INVALID",
+  LEARNING_RESPONSE_INVALID: "LEARNING_RESPONSE_INVALID",
   LEARNING_SKILLS_BUNDLE_INVALID: "LEARNING_SKILLS_BUNDLE_INVALID",
   LEARNING_SKILLS_INTEGRITY_FAILED: "LEARNING_SKILLS_INTEGRITY_FAILED",
   LEARNING_SKILLS_OUTPUT_EXISTS: "LEARNING_SKILLS_OUTPUT_EXISTS"
@@ -15173,20 +15180,18 @@ var FRAMEWORK_TEMPLATES = {
       TEMPLATE_REPOS["microsoft-agent-framework-dotnet"],
       `\u{1FA81}\u{1F91D}${FRAMEWORK_EMOJI["microsoft-agent-framework-dotnet"]}`
     ),
-    // No root-`.env` vendor gate: the agent's model credentials are configured
-    // via dotnet user-secrets (GitHub Models, by default) or OpenAI/Azure
-    // OpenAI, none of which live in the root `.env`, so a fixed root-`.env` key
-    // requirement would falsely warn. The GitHub-token user-secrets command is
-    // credential setup (not a generic post-install build step), so it is
-    // surfaced as explicit credential guidance below instead.
+    // No root-`.env` vendor gate: the agent's OpenAI credential is configured
+    // via dotnet user-secrets. It does not live in the root `.env`, so a fixed
+    // root-`.env` key requirement would falsely warn. The user-secrets command
+    // is credential setup (not a generic post-install build step), so it is
+    // surfaced as explicit guidance below.
     environment: [],
     setupNotes: [
       { text: "  Set up the agent model credentials:" },
       {
-        text: "    GitHub Models:  ",
-        code: 'cd agent && dotnet user-secrets set GitHubToken "<your-github-token>"'
-      },
-      { text: "    or OpenAI / Azure OpenAI \u2014 see the agent README" }
+        text: "    OpenAI:  ",
+        code: 'cd agent && dotnet user-secrets set OPENAI_API_KEY "<your-openai-api-key>"'
+      }
     ]
   },
   "microsoft-agent-framework-py": {
@@ -15487,6 +15492,27 @@ async function scaffoldStarterForSmoke(input, scaffold = scaffoldProject) {
     }
     await scaffold({ projectDir, template: configuredTemplate });
     await definition.postScaffold?.(projectDir);
+    if (input.framework === "microsoft-agent-framework-dotnet") {
+      const command = definition.setupNotes?.find(
+        (note) => note.code?.includes("dotnet user-secrets set")
+      )?.code;
+      const credential = command?.match(
+        /dotnet user-secrets set ([A-Za-z0-9_]+)/
+      )?.[1];
+      const programPath = path4.join(projectDir, "agent", "Program.cs");
+      const program = fs4.existsSync(programPath) ? fs4.readFileSync(programPath, "utf8") : "";
+      if (!credential || !program.includes(credential)) {
+        throw new StarterSmokeError(
+          "STARTER_CREDENTIAL_MISMATCH",
+          "Microsoft Agent Framework .NET credential guidance does not match the bound starter",
+          {
+            framework: input.framework,
+            credential,
+            revision: input.template.revision
+          }
+        );
+      }
+    }
     const entries = fs4.readdirSync(projectDir);
     return entries.join("\n");
   } finally {