copilotkit 4.14.0 → 4.16.0

package/onboarding/prompts/starter/clone.md

@@ -52,7 +52,7 @@ 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@4.14.0 project list --json`
+`npx --prefer-offline --yes copilotkit@4.16.0 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
@@ -79,7 +79,7 @@ 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@4.14.0 init --name <directory-name> --framework <framework-id> --channel none --no-banner --no-key-prompt --create <name> --install`
+`npx --prefer-offline --yes copilotkit@4.16.0 init --name <directory-name> --framework <framework-id> --channel none --no-banner --no-key-prompt --create <name> --install`
 
 `--name` is always the target directory name derived above, because `init` creates the
 app at `<parent>/<name>`. Any other value puts the app in a new folder beside the target,
@@ -91,6 +91,13 @@ the dependency install, use
 answer as a flag. `--no-key-prompt` stops `init` from asking for a model key. The `init`
 output still names each missing key as `Set <VARIABLE> in .env`.
 
+If the developer named a key file, add `--model-key-file <key-file>` with the path they gave.
+`init` copies only the variable the starter needs into the starter's own env file,
+including `agent/.env` for the Microsoft Agent Framework Python starter. It prints the
+variable name and never the value. Do not read or copy the key file yourself. If `init`
+reports that it cannot read the model key file, it stopped before it cloned anything. Ask
+the developer for the right path, or run the command again without the flag.
+
 The command clones the starter into the empty target directory. It also connects the
 starter to the developer's Intelligence project. The earlier login phase supplies the
 account. The command does not need terminal input.
@@ -98,7 +105,7 @@ account. The command does not need terminal input.
 Report the clone before you inspect anything:
 
 ```text
-npx --yes copilotkit@4.14.0 onboard checkpoint --phase starter-cloned
+npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase starter-cloned
 ```
 
 This is its own step, not an aside. A run that clones and then goes quiet is
@@ -111,6 +118,10 @@ and validation commands.
 
 ## Settle the model credential
 
+The `init` output names each key it copied from a key file as
+`Copied <VARIABLE> from the model key file into <file>`. A copied key is in place, so do
+not check it. If the key file did not hold a variable, the output warns by name.
+
 The `init` output names each missing credential as `Set <VARIABLE> in .env`. For each
 one, check the starter's own `.env` without reading the value:
 
@@ -121,19 +132,15 @@ grep -c '^<VARIABLE>=.' <target>/.env
 `1` means the variable holds a value. `0` means it is empty or absent. The command prints
 a count and never the value.
 
-If the developer named a key file, copy that one variable from it into `<target>/.env`,
-in place of the empty line. Do not print either file, and do not print the value. Then
-run the check again.
-
-If a variable is still empty, ask the developer to add it to `<target>/.env` themselves.
+If a variable is empty, ask the developer to add it to `<target>/.env` themselves.
 
 The two Microsoft Agent Framework starters keep their key outside `<target>/.env`, so
 `init` prints no `Set` line for them. Settle the key from the Model key column instead:
 
-- For the Python starter, run the same check for `OPENAI_API_KEY` against
-  `<target>/agent/.env`. A missing file counts as `0`. If the developer named a key file,
-  copy the variable into `<target>/agent/.env` the same way. If it is still empty, ask the
-  developer to add it there themselves.
+- For the Python starter, a key file passed to `init` fills `<target>/agent/.env`, and the
+  output says so. Otherwise, run the same check for `OPENAI_API_KEY` against
+  `<target>/agent/.env`. A missing file counts as `0`. If it is empty, ask the developer to
+  add it there themselves.
 - For the .NET starter, the key lives in `dotnet user-secrets`, and no check can read it
   without printing the value. Ask the developer to run
   `cd <target>/agent && dotnet user-secrets set OPENAI_API_KEY "<key>"` themselves, even
@@ -142,7 +149,7 @@ The two Microsoft Agent Framework starters keep their key outside `<target>/.env
 Then report the pause and end your turn:
 
 ```text
-npx --yes copilotkit@4.14.0 onboard checkpoint --phase awaiting-developer
+npx --prefer-offline --yes copilotkit@4.16.0 onboard checkpoint --phase awaiting-developer
 ```
 
 This is a pause, not a stop. Do not send a stop report, and do not take a stop route.
@@ -153,10 +160,10 @@ call.
 
 If no credential is missing, report no pause and continue.
 
-Then run `npx --yes copilotkit@4.14.0 onboard read proof/round-trip`.
+Then run `npx --prefer-offline --yes copilotkit@4.16.0 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@4.14.0 onboard read stopped/run-failed`. The starter is one this
+`npx --prefer-offline --yes copilotkit@4.16.0 onboard read stopped/run-failed`. The starter is one this
 graph ships and the stack was chosen from its own supported list, so a command that
 returned an error is a run that broke, not a setup this release does not support.

package/onboarding/prompts/stopped/run-failed.md

@@ -23,6 +23,12 @@ Say what the developer has now. Name the processes still running and the files t
 changed, so they can carry on by hand or start again from a known state. A run that stops
 without saying what it left behind leaves the developer to discover it.
 
+A step can fail on a network error: `EAI_AGAIN`, `ECONNRESET`, `ETIMEDOUT`, a timeout,
+or a message that names a proxy. The CLI has already tried that step again. Ask the
+developer to check their network, VPN, or proxy setting. This fix needs no file changes.
+When the network works, propose it as the one fix below, and come back with
+`onboard resume`.
+
 ## If one scoped fix can finish this run
 
 Do not decide this yourself. This run refused to widen its own scope, and that refusal
@@ -35,10 +41,10 @@ put to them, stop here and send the report below.
 If they approve it, make that one fix and nothing else. Then come back into this run:
 
 ```text
-npx --yes copilotkit@4.14.0 onboard resume
+npx --prefer-offline --yes copilotkit@4.16.0 onboard resume --message "<approval>"
 ```
 
-Write the developer's approval to standard input, in one or two sentences: the fix they
+Put the developer's approval in `--message`, in one or two sentences: the fix they
 approved and what it touches. Send no secrets, source code, logs, or command output. The
 command refuses an approval that carries any of those, prints the reason, exits zero, and
 serves nothing. Reword it and send it again.
@@ -58,10 +64,10 @@ Send one short report. Run the friction command without another developer questi
 ask the developer about telemetry: the command applies the setting they already have.
 
 ```text
-npx --yes copilotkit@4.14.0 onboard friction --phase stop --category <slug>
+npx --prefer-offline --yes copilotkit@4.16.0 onboard friction --phase stop --category <slug> --message "<sentences>"
 ```
 
-Write one or two sentences to standard input: the step you stopped at and what stopped
+`--message` takes one or two sentences: 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

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

@@ -170,7 +170,7 @@ 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@4.14.0 verify --round-trip`, which needs no browser. Do not plan a
+`npx --prefer-offline --yes copilotkit@4.16.0 verify --round-trip`, which needs no browser. Do not plan a
 step that opens the managed Intelligence dashboard.
 
 ## Order the plan into steps

package/onboarding/prompts/subagent/inspect-repository.md

@@ -7,7 +7,7 @@ Work only on the packet you were assigned. Inspect the repository without changi
 Run this first, from the target project directory:
 
 ```text
-npx --yes copilotkit@4.14.0 onboard inspect --json
+npx --prefer-offline --yes copilotkit@4.16.0 onboard inspect --json
 ```
 
 It answers the deterministic half of both packets exactly, from the same code

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

@@ -7,6 +7,19 @@ Find the expected agent id from the project. Start the existing agent and fronte
 when they are not already running. Before using a port, identify its process and working
 directory. Do not stop a process outside this project.
 
+`next dev` locks its build directory, not its port. Next 16 writes `.next/dev/lock`. A
+second `next dev` in the same app exits with `Unable to acquire lock at ..., is another
+instance of next dev running?`. A free port does not help. If a `next dev` process already
+runs from this app, reuse that server. Prove against its port. If a start still fails with
+that message, name the process that holds the lock. Give its PID and working directory.
+
+If your harness runs commands in a sandbox, a sandboxed command cannot listen on a port or
+connect to localhost. Before the first server start, request escalation with a prefix rule
+for the project's own dev script. Before the first request to a local server, request
+escalation with a prefix rule for `curl`. If a local request still fails after 0 ms
+(`Failed to connect ... after 0 ms`) while the port shows a listener, the sandbox blocked
+it. Run it again with escalation, and do not record a failed predicate or step.
+
 Prove the live runtime in this order:
 
 1. GET `/info` from the project's CopilotKit runtime and require a valid response.
@@ -19,7 +32,7 @@ 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@4.14.0 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
+   `npx --prefer-offline --yes copilotkit@4.16.0 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

@@ -89,21 +89,33 @@ agent and the frontend from one `dev` script, which runs them under
 other. A second start against a project already running that script collides with a server
 that is up.
 
+`next dev` locks its build directory, not its port. Next 16 writes `.next/dev/lock`. A
+second `next dev` in the same app exits with `Unable to acquire lock at ..., is another
+instance of next dev running?`. A free port does not help.
+
+Before you start a Next.js frontend, look for a `next dev` process that runs from this app.
+If one runs, reuse that server. Read its port from its command line or its listener, and
+prove against that port. If a start still fails with that message, name the process that
+holds the lock. Give its PID and working directory. Do not stop it unless it belongs to
+this project.
+
+If your harness runs commands in a sandbox, a sandboxed command cannot listen on a port or
+connect to localhost. Before the first server start, request escalation with a prefix rule
+for the project's own dev script. Before the first request to a local server, request
+escalation with a prefix rule for `curl`. If a local request still fails after 0 ms
+(`Failed to connect ... after 0 ms`) while the port shows a listener, the sandbox blocked
+it. Run it again with escalation, and do not record a failed predicate or step.
+
 Start each server in the background with the project's own script. Then wait for it to
 answer rather than for a fixed number of seconds:
 
 ```bash
-ready=
-for _ in $(seq 90); do
-  curl -fs -o /dev/null "<url>" && ready=1 && break
-  sleep 1
-done
-[ "$ready" = 1 ] && echo "up" || echo "no answer from <url> after 90 seconds"
+curl -fs -o /dev/null --retry 90 --retry-delay 1 --retry-max-time 90 --retry-all-errors "<url>"
 ```
 
-Read the loop's own last line rather than assuming it ended because the server answered.
-A server that never answered has written the reason to its own output, and reading that
-output is faster than starting it again.
+A zero exit means the server answered. Any other exit means that it did not answer in 90
+seconds. A server that never answered has written the reason to its own output, and
+reading that output is faster than starting it again.
 
 That coupling also turns an ordinary restart into a false failure. Where you stop a server
 to pick up an installed dependency, start both again and wait for both to answer before you
@@ -145,7 +157,7 @@ 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@4.14.0 verify --json`. It reads the port from this project, so a
+`npx --prefer-offline --yes copilotkit@4.16.0 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
@@ -179,7 +191,7 @@ named no port the CLI can read: keep step 2's URL, and rewrite its host as `loca
 before you use it.
 
 Then run the command once more with the URL you are about to open:
-`npx --yes copilotkit@4.14.0 verify --frontend-url <that url> --json`. The
+`npx --prefer-offline --yes copilotkit@4.16.0 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
@@ -187,7 +199,7 @@ is the cheapest step that can save the most expensive one, so run it before the
 
 ## Step 5 -- Prove that the agent runs
 
-Run `npx --yes copilotkit@4.14.0 verify --round-trip --json`. It sends one request through
+Run `npx --prefer-offline --yes copilotkit@4.16.0 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
@@ -200,7 +212,7 @@ Where this run settled a Learning Container, add the flag to the call above rath
 running a second round trip:
 
 ```text
-npx --yes copilotkit@4.14.0 verify --round-trip --expect-learning-container <container id> --json
+npx --prefer-offline --yes copilotkit@4.16.0 verify --round-trip --expect-learning-container <container id> --json
 ```
 
 The check reads the thread that this run created, so a second round trip proves a second
@@ -234,7 +246,7 @@ the credential was written holds an empty key while the file beside it carries t
 one. Run this from the target app directory:
 
 ```text
-npx --yes copilotkit@4.14.0 onboard env-staleness
+npx --prefer-offline --yes copilotkit@4.16.0 onboard env-staleness
 ```
 
 A `stale` line names the env file and how long after launch it was written. Report that,
@@ -312,7 +324,7 @@ 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@4.14.0 verify --round-trip`, which reads the
+that thread with `npx --prefer-offline --yes copilotkit@4.16.0 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
@@ -340,7 +352,7 @@ request never exercises. Drive it with the browser control step 6 named.
    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@4.14.0 verify --frontend-url <the url you opened> --json`
+   `npx --prefer-offline --yes copilotkit@4.16.0 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.

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

@@ -30,16 +30,16 @@ 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@4.14.0 onboard read fallback/best-effort`.
+`npx --prefer-offline --yes copilotkit@4.16.0 onboard read fallback/best-effort`.
 
 Send one short report. Run the friction command without another developer question. Do not
 ask the developer about telemetry: the command applies the setting they already have.
 
 ```text
-npx --yes copilotkit@4.14.0 onboard friction --phase stop --category <slug>
+npx --prefer-offline --yes copilotkit@4.16.0 onboard friction --phase stop --category <slug> --message "<sentences>"
 ```
 
-Write one or two sentences to standard input: the step you stopped at and what stopped it.
+`--message` takes one or two sentences: 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

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "copilotkit",
-  "version": "4.14.0",
+  "version": "4.16.0",
   "type": "module",
   "engines": {
     "node": ">=20.9.0"

package/release/release-tool.js

@@ -14811,7 +14811,7 @@ var FLAG_DEFINITIONS = defineFlags({
 
 // apps/cli/src/config.ts
 function getTemplateRef() {
-  return true ? "2c42a41a7e749c4473705769d1ae985d89718465" : "main";
+  return true ? "a933af0b132e61d2d04be7ce0a8f55743af21ccc" : "main";
 }
 
 // apps/cli/src/services/agentcore-config.ts
@@ -15320,6 +15320,7 @@ var FRAMEWORK_TEMPLATES = {
     // key requirement here would falsely warn on valid Azure/`agent/.env`
     // setups — the guidance below points at `agent/.env` instead.
     environment: [],
+    modelKeyTargets: [{ key: "OPENAI_API_KEY", envFile: "agent/.env" }],
     setupNotes: [
       { text: "  Set up the agent model credentials in agent/.env:" },
       { text: "    OpenAI:  ", code: "OPENAI_API_KEY=sk-..." },
@@ -15511,24 +15512,68 @@ function readEntries(dir) {
   }
 }
 function findProjectsBelow(dir) {
+  return walkProjectsBelow(dir, readEntries(dir), {
+    stopAfter: Number.POSITIVE_INFINITY,
+    maxEntries: Number.POSITIVE_INFINITY
+  }).found.sort();
+}
+function readEntriesUpTo(dir, limit) {
+  if (limit === Number.POSITIVE_INFINITY) {
+    return {
+      entries: fs4.readdirSync(dir, { withFileTypes: true }),
+      exhausted: false
+    };
+  }
+  const handle = fs4.opendirSync(dir);
+  const entries = [];
+  try {
+    for (let entry = handle.readSync(); entry !== null; entry = handle.readSync()) {
+      if (entries.length >= limit)
+        return { entries, exhausted: true };
+      entries.push(entry);
+    }
+    return { entries, exhausted: false };
+  } finally {
+    handle.closeSync();
+  }
+}
+function walkProjectsBelow(dir, top, limits) {
   const found = [];
-  const visit = (relative, depth) => {
-    for (const entry of readEntries(path4.join(dir, relative))) {
+  let budget = limits.maxEntries - top.length;
+  let exhausted = budget < 0;
+  const readChild = (childDir) => {
+    try {
+      const read = readEntriesUpTo(childDir, budget);
+      budget -= read.entries.length;
+      if (read.exhausted)
+        exhausted = true;
+      return read.entries;
+    } catch {
+      return [];
+    }
+  };
+  const visit = (relative, entries, depth) => {
+    for (const entry of entries) {
+      if (found.length >= limits.stopAfter || exhausted)
+        return;
       if (!entry.isDirectory())
         continue;
       if (entry.name.startsWith(".") || entry.name === "node_modules")
         continue;
       const child = path4.join(relative, entry.name);
-      const names = readEntries(path4.join(dir, child)).map((e) => e.name);
+      const childEntries = readChild(path4.join(dir, child));
+      if (exhausted)
+        return;
+      const names = childEntries.map((e) => e.name);
       if (names.some((n) => n === ".git" || PROJECT_MANIFEST_NAMES.has(n))) {
         found.push(child);
       } else if (depth < PROJECTS_BELOW_DEPTH) {
-        visit(child, depth + 1);
+        visit(child, childEntries, depth + 1);
       }
     }
   };
-  visit("", 1);
-  return found.sort();
+  visit("", top, 1);
+  return { found, exhausted };
 }
 function readProjectDirContents(projectDir, homeDir = os.homedir()) {
   if (!fs4.existsSync(projectDir))