copilotkit 4.13.1 → 4.15.0

package/onboarding/prompts/subagent/implement-and-validate.md

@@ -10,7 +10,7 @@ either path is an ancestor directory on a path-segment boundary. `apps/a` overla
 `apps/a/src`, but not `apps/ab`. `app.ts` does not overlap `app.tsx`.
 
 Change only the files and directories the approved plan names as changeable. If the work
-requires a file the plan does not name, stop and return the blocker. Do not run a
+requires a file the plan does not name, return the blocker and end your turn. Do not run a
 repository-wide formatter.
 
 All implementation work happens in the run root's own working tree: the target app
@@ -54,6 +54,17 @@ connection. Do not read, show, store, or return secrets. Do not read a file outs
 project directory: not for a credential, and not for an API question the fetched
 documentation answers. Ask the main coding agent for a missing credential.
 
+Before running a scaffolder, check whether it writes an environment file. Never replace
+an existing `.env` with `.env.example` or scaffolder output. Preserve its existing bytes,
+including the provisioned Intelligence key. Do not use shell redirection or a force flag
+to bypass this rule.
+
+If the scaffolder cannot preserve a protected file, generate into a temporary directory
+inside the project only when the approved plan permits it. Copy only approved paths that
+do not overlap a protected path. Otherwise, return the conflict and end your turn before
+running the scaffolder. Ask the main coding agent to revise credential setup when a
+required variable is missing. Do not provision another key to repair a scaffold overwrite.
+
 ## What the existing agent's behavior is
 
 The existing agent's behavior is four things: its system prompt and instructions, its
@@ -112,8 +123,8 @@ it fails in the threads drawer rather than at the install.
 
 If one of them resolves to more than one version, restore the manifest and lockfile to
 their recorded state, leave Intelligence unwired, and report which package resolved to more
-than one version, which versions, and which declared range held the top of the tree. Stop.
-Do not wire Intelligence onto a tree carrying two copies of a package.
+than one version, which versions, and which declared range held the top of the tree. Then
+end your turn. Do not wire Intelligence onto a tree carrying two copies of a package.
 
 Never add an `overrides`, `resolutions`, or `pnpm.overrides` block to collapse the two
 copies. It forces a version the developer did not approve onto their whole tree, and it
@@ -121,8 +132,9 @@ turns a reportable mismatch between two published packages into a local workarou
 else can see.
 
 If the baseline regresses, restore the manifest and lockfile to their recorded state, leave
-Intelligence unwired, and report the regression with the failing check. Stop. Where the plan
-names no dependency change, report that the installed versions met the floor.
+Intelligence unwired, and report the regression with the failing check. Then end your
+turn. Where the plan names no dependency change, report that the installed versions met
+the floor.
 
 When the documentation uses the framework's scaffolder,
 run that scaffolder rather than hand-authoring what it emits.
@@ -165,4 +177,5 @@ command rather than running them one at a time. Split a command only when its re
 what you run next.
 
 Start with `Status: passed`, `Status: failed`, or `Status: blocked`.
-Return exactly four sections: Status, Files changed, Validation, and Blockers. Stop.
+Return exactly four sections: Status, Files changed, Validation, and Blockers. Then end
+your turn.

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@4.13.1 onboard inspect --json
+npx --prefer-offline --yes copilotkit@4.15.0 onboard inspect --json
 ```
 
 It answers the deterministic half of both packets exactly, from the same code
@@ -87,4 +87,4 @@ Use only `proved`, `absent`, or `unproved` for the status. State each absent or
 Do not read, print, or return secret values. For `.env` and `.copilotkit/project.json`
 checks, return only paths, presence checks, and missing field names. Do not read a file
 outside the project directory. Do not run or return an onboarding command other than
-`onboard inspect`. Stop after returning the findings to the main coding agent.
+`onboard inspect`. End your turn after returning the findings to the main coding agent.

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

@@ -7,6 +7,13 @@ 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.
 
+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 +26,7 @@ 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@4.13.1 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
+   `npx --prefer-offline --yes copilotkit@4.15.0 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
@@ -45,4 +52,4 @@ can be durable. Report the persistence that project evidence proves, or `unprove
 replace it and do not describe all OSS runs as ephemeral.
 
 Start with `Status: passed`, `Status: failed`, or `Status: blocked`.
-Stop after returning the baseline result, process ids and ports used, and evidence paths.
+End your turn after returning the baseline result, process ids and ports used, and evidence paths.

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

@@ -13,8 +13,8 @@ The existing agent's behavior is outside every step of this proof. It is four th
 agent's system prompt and instructions, its tools and what those tools do, its model and
 provider configuration, and its memory or state handling. A failing predicate is repaired
 on the CopilotKit side -- the frontend rendering, the tool schema, the runtime wiring.
-Where the only fix you can find is a change to the agent's instructions or tools, stop and
-return the failing predicate with the change you propose, for the developer to approve.
+Where the only fix you can find is a change to the agent's instructions or tools, return
+the failing predicate with the change you propose, for the developer to approve.
 Such a change is a behavior change rather than a repair: it changes how the agent answers
 everywhere, not only in CopilotKit. Never rewrite the agent's prompt to make a component
 render, and never report a round trip proved by a prompt this run rewrote.
@@ -89,21 +89,23 @@ 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.
 
+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 +147,7 @@ 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@4.13.1 verify --json`. It reads the port from this project, so a
+`npx --prefer-offline --yes copilotkit@4.15.0 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 +181,7 @@ 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@4.13.1 verify --frontend-url <that url> --json`. The
+`npx --prefer-offline --yes copilotkit@4.15.0 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 +189,7 @@ 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@4.13.1 verify --round-trip --json`. It sends one request through
+Run `npx --prefer-offline --yes copilotkit@4.15.0 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 +202,7 @@ Where this run settled a Learning Container, add the flag to the call above rath
 running a second round trip:
 
 ```text
-npx --yes copilotkit@4.13.1 verify --round-trip --expect-learning-container <container id> --json
+npx --prefer-offline --yes copilotkit@4.15.0 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 +236,7 @@ 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@4.13.1 onboard env-staleness
+npx --prefer-offline --yes copilotkit@4.15.0 onboard env-staleness
 ```
 
 A `stale` line names the env file and how long after launch it was written. Report that,
@@ -312,7 +314,7 @@ 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@4.13.1 verify --round-trip`, which reads the
+that thread with `npx --prefer-offline --yes copilotkit@4.15.0 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 +342,7 @@ 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@4.13.1 verify --frontend-url <the url you opened> --json`
+   `npx --prefer-offline --yes copilotkit@4.15.0 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.
@@ -489,4 +491,4 @@ standard blocked completion route. Use `Status: failed` for a failed proof step.
 Return the proof or the exact failed step to the main coding agent, together with the
 input, the visible result, the relevant process status, the evidence locations, the
 surface-check outcome, and which surface that outcome speaks for. Do not return secret
-values. Stop after you return the result.
+values. End your turn after you return the result.

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@4.13.1 onboard read fallback/best-effort`.
+`npx --prefer-offline --yes copilotkit@4.15.0 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@4.13.1 onboard friction --phase stop --category <slug>
+npx --prefer-offline --yes copilotkit@4.15.0 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": "4.13.1",
+  "version": "4.15.0",
   "type": "module",
   "engines": {
     "node": ">=20.9.0"
@@ -16,5 +16,9 @@
   "optionalDependencies": {
     "@microsoft/teams.cli": "3.0.3"
   },
+  "dependencies": {
+    "@mastra/core": "1.48.0",
+    "@mastra/libsql": "1.14.3"
+  },
   "license": "SEE LICENSE IN LICENSE"
 }