copilotkit 4.27.0 → 4.29.0

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

@@ -3,6 +3,19 @@
 Read and run only inside the project directory. Do not edit source, configuration,
 dependencies, or tracked files. Do not read, show, store, or return secret values.
 
+## When a command is refused
+
+If you are a subagent and your harness refuses a command, return at once. Name the
+command, the directory you ran it from, and the refusal, and run nothing else. Do not wait
+for an approval: nobody sees it. The main coding agent runs the command itself and passes
+the result on. The one wait allowed is a harness escalation request that this brief tells
+you to make for a command. Make that request and wait for its answer.
+
+If your handoff holds a command's result, use it and do not run that command again.
+
+If you are the main coding agent and follow this brief yourself, this section is not for
+you. Do not return: handle a refused command as the run's other prompts say.
+
 Find the expected agent id from the project. Start the existing agent and frontend only
 when they are not already running. Before using a port, identify its process and working
 directory. Do not stop a process outside this project.
@@ -35,7 +48,7 @@ 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 --prefer-offline --yes copilotkit@4.27.0 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
+   `npx --prefer-offline --yes copilotkit@4.29.0 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
    with the runtime URL or auth header options that this project needs. Add
    `--runtime-url <url>` when the report names a runtime URL the dev server does not
    serve. Require exit zero
@@ -68,5 +81,15 @@ The default in-memory OSS runner is ephemeral. SQLite, custom, or framework pers
 can be durable. Report the persistence that project evidence proves, or `unproved`. Do not
 replace it and do not describe all OSS runs as ephemeral.
 
+Before you return, record that you are returning:
+
+```text
+npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase subagent-returned --brief prove-oss-baseline --result <ok|failed>
+```
+
+The Status line of your result decides the value. Pass `ok` only for `Status: passed`.
+Pass `failed` for `Status: failed` or `Status: blocked`. If your harness refuses this command, say so in your result and return
+anyway: the main coding agent records it.
+
 Start with `Status: passed`, `Status: failed`, or `Status: blocked`.
 End your turn after returning the baseline result, process ids and ports used, and evidence paths.

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

@@ -30,7 +30,7 @@ the steps name: no SDK calls, AG-UI requests, or thread reads of your own to con
 journey's frontend, and run only that one.
 
 A run that cloned a starter is the one exception. When the main coding agent tells you
-that this run cloned a starter, run Step 1 and the proof checks, then go to Step 10. Skip Steps 5a through 9, open no browser
+that this run cloned a starter, run Step 1 and the proof checks, then go to Step 9. Skip Steps 5a through 8, open no browser
 or device, and report `skipped-cloned-starter` as the surface-check outcome.
 
 Where this is a second attempt after a repair, run every step from the proof checks through
@@ -50,6 +50,19 @@ Gather what you need in as few commands as possible. Combine independent reads i
 command rather than running them one at a time. Split a command only when its result decides
 what you run next.
 
+## When a command is refused
+
+If you are a subagent and your harness refuses a command, return at once. Name the
+command, the directory you ran it from, and the refusal, and run nothing else. Do not wait
+for an approval: nobody sees it. The main coding agent runs the command itself and passes
+the result on. The one wait allowed is a harness escalation request that this brief tells
+you to make for a command. Make that request and wait for its answer.
+
+If your handoff holds a command's result, use it and do not run that command again.
+
+If you are the main coding agent and follow this brief yourself, this section is not for
+you. Do not return: handle a refused command as the run's other prompts say.
+
 ## Step 1 -- Read what the proof needs
 
 Read all of this from the approved plan in one pass, before you start anything:
@@ -76,7 +89,7 @@ about the failure it was spawned to clear.
 Run this from the target app directory:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.27.0 onboard proof-check --json
+npx --prefer-offline --yes copilotkit@4.29.0 onboard proof-check --json
 ```
 
 It starts each app's `dev` script unless a server from that app already listens, and
@@ -132,7 +145,7 @@ Otherwise sort `firstFailure`, and run the command again after each repair:
   asking. Read the port from the log, not from the plan, and record it:
 
   ```text
-  npx --prefer-offline --yes copilotkit@4.27.0 onboard runtime-url --url <runtime-url>
+  npx --prefer-offline --yes copilotkit@4.29.0 onboard runtime-url --url <runtime-url>
   ```
 
   `<runtime-url>` is the project's runtime URL, or the plan's, with its port replaced by the
@@ -177,6 +190,13 @@ Otherwise sort `firstFailure`, and run the command again after each repair:
 
   Where the handoff carries a thread id from the developer, skip the numbered steps above
   and do not open the app for them. Run the checks with `--thread <id>` at once.
+- `round-trip:page_context_reaches_agent` with a detail that says the starter does not pass
+  page context yet: it is marked `advisory`, and the checks pass. This framework's starter
+  and its AG-UI adapter keep the page's context off the model's prompt. That is a known gap,
+  not a fault of this run. Do not repair the adapter. Still run Step 5a where it applies. If
+  its context comparison fails, record that under the same warning rather than as a failed
+  step. Return the warning with the proof result. The rules below are for every other
+  page-context result.
 - `round-trip:page_context_reaches_agent` at `fail`: the agent answered the plain request
   and recorded nothing for the request that carried context. Return it with its evidence as
   a failed proof step. At `undetermined` and marked `advisory`, the agent answered without
@@ -212,10 +232,11 @@ for the same reason. Skip both steps and send no run. Record that they sent no r
 reason, and prove the page's data and the component in the browser instead, at Steps 6
 and 7.
 
-`verify --round-trip` asks a question that needs no context. Where the frontend's files
-call a context hook, it also sends one token as context and reports
-`page_context_reaches_agent`, whose `pass` proves that the agent's model sees context at
-all. An agent scoped to its own task answers without the token, so that check is often
+`verify --round-trip` asks a question that needs no context. It then sends one token as
+context and reports `page_context_reaches_agent`, also where the frontend's files call no
+context hook, because the CopilotKit frontend sends context entries of its own. Without a
+context hook, a `pass` proves only that a run with context answers. Where the files call a
+context hook, a `pass` proves that the agent's model sees context at all. An agent scoped to its own task answers without the token, so that check is often
 `undetermined`, and this step is then the only proof of the path. A `pass` does not prove
 that the page's own entries arrive in the shape the agent reads. Nothing else before the
 browser reads that path, so a page whose data the agent never sees answers fluently over a
@@ -228,9 +249,15 @@ the agent sees the request the browser sends rather than a thinner one. Read the
 files the main coding agent named in the handoff, and search the project only for a file it
 did not name. Do not search the dependencies for the shape of an entry: the page's own call
 shows it. Send the same run
-body twice, to `<runtime>/agent/<agent id>/run`: once carrying the context entries the page
+body twice: once carrying the context entries the page
 publishes, and once carrying the same entries with one value changed. Use the step 1
-request both times. Record the streamed events from each, and name both capture paths.
+request both times. Write each body to a JSON file in `.copilotkit/proof/`, and send it with
+`npx --prefer-offline --yes copilotkit@4.29.0 verify --send-run <file> --agent <agent id> --json`.
+The command sends the body to `<runtime>/agent/<agent id>/run` and reads the events the run
+streams. It writes them to `<file name>.events.jsonl` beside the body, and prints that path
+with the answer text and the tool calls. Do not send a run with `curl` and read its events
+with a client of your own. A managed runtime streams the events over the gateway, behind a
+join token that expires 30 seconds after the run starts. Name both capture paths.
 
 For the changed run, pick one record the step 1 request matches. Add a marker to a text
 field that the answer repeats and that the step 1 request does not quote, such as its title
@@ -243,7 +270,8 @@ nothing to copy invents records. That failure belongs to the probe, not to the i
 
 Read each answer against the context it carried. The run carrying the page's context has to
 name the project's own records and no others. The run carrying the changed entry has to
-carry the marker, character for character, and name no record its context did not hold. A
+carry the marker's 8 hex characters anywhere in it, in any case and with any punctuation
+around them, and name no record its context did not hold. The model can reword the rest. A
 model that the context never reaches cannot produce the marker. A model that invents a
 different record on every call cannot produce it either, so two answers that only differ
 prove nothing. An answer without the marker means the page's data is not reaching the model.
@@ -270,8 +298,8 @@ Read the registrations this project's frontend declares, by name. Step 5a alread
 step 1 request with those declarations, so read the tool calls out of the events Step 5a
 captured for the run carrying the page's unchanged context. Do not send that request again.
 Where Step 5a sent no run because the proof checks needed `--thread`, send no run here
-either. Where Step 5a sent no run, because this journey shares no page data, send the step 1 request
-to `<runtime>/agent/<agent id>/run`, carrying those declarations, and read the tool calls out
+either. Where Step 5a sent no run, because this journey shares no page data, send the step 1 request,
+carrying those declarations, with `verify --send-run` the way Step 5a does, and read the tool calls out
 of that run's own events. Where the Step 5a run carried none of those declarations, send
 that run once more with them, and read that run instead. Never report a wiring gap from a run
 that carried no declarations: the agent has no component to call in it. The agent has to call one of the names the frontend registered. An
@@ -302,7 +330,7 @@ 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 --prefer-offline --yes copilotkit@4.27.0 verify --round-trip`, which reads the
+that thread with `npx --prefer-offline --yes copilotkit@4.29.0 verify --round-trip`, which reads the
 answer back off the thread and needs no browser. Where the proof checks needed `--thread`,
 prove the thread for this request with `verify --thread <id>` instead. Record which of the
 two you proved.
@@ -332,7 +360,7 @@ limit can be ten minutes. You cannot interrupt a call while it runs, so the limi
 what you do after one. If a browser call took longer than 60 seconds to return, the browser
 control is unresponsive. Do not call the browser again in this attempt. A second call to a
 hung tool waits as long as the first one did. Run
-`npx --prefer-offline --yes copilotkit@4.27.0 verify --frontend-url <the frontendUrl the proof checks resolved> --json` once,
+`npx --prefer-offline --yes copilotkit@4.29.0 verify --frontend-url <the frontendUrl the proof checks resolved> --json` once,
 and record the `frontend_assets_served` result. Report the outcome `failed` with the cause
 `browser-control-unresponsive`. The application is not at fault on this evidence: every
 step before the browser proved the runtime without one, and no repair to the project can
@@ -342,7 +370,7 @@ reach the tool.
    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 --prefer-offline --yes copilotkit@4.27.0 verify --frontend-url <the url you opened> --json`
+   `npx --prefer-offline --yes copilotkit@4.29.0 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.
@@ -356,7 +384,10 @@ reach the tool.
    turn is finished when the streamed text stops growing and the generative UI component
    has rendered. For a recorded `both-oss` starting state, this step has no component, and
    the turn is finished when the streamed text stops growing.
-6. Take one screenshot of the finished turn and record where you wrote it.
+6. Take one screenshot of the finished turn, and record its path. Where the browser tool
+   takes a path, save it in `.copilotkit/proof/`. A tool that writes into its own output
+   folder, such as `.playwright-mcp/`, can keep it there. Never save it among the project's
+   own files.
 7. Read the browser console a second time, and record every error that step 3 did not
    already list. Those belong to the request.
 8. Read the network requests. Record every request the page made to the runtime endpoint
@@ -446,42 +477,17 @@ it, rather than reading the compatibility field as a pass.
 
 For every other starting state, record Step 8 as not applicable.
 
-The application edit ban ends only after Step 8 passes or is recorded as not applicable.
-Step 9 can write only the tool files named by its guide or by this step.
-
-## Step 9 -- Set up the continued-development tools
-
-Fetch the continued-development guide from the main coding agent with the proof
-documentation. Try the continued-development tools after the application passes proof.
-
-The implementation subagent installs the Skills unless the developer declined them. Check that
-it did. Look for the `.agents/skills` directory and the `.claude/skills` links in this
-project, and read the Skills result the implementation reported. Do not install them again.
+## Step 9 -- Return the result
 
-Where the developer declined them, do not install them, and do not call that a change from
-the plan. Report the command for them to run later instead:
-`npx skills add CopilotKit/CopilotKit/skills -y`.
+Before you return, record that you are returning:
 
-Where the developer did not decline them and they are missing, install them as a recovery step.
-Tell the developer what the skills install writes into this project before you run it: a
-`.agents/skills` directory holding one folder per CopilotKit skill, linked into
-`.claude/skills`. Both sit in the working tree, so the install shows up in `git status`
-and can land in a commit. You cannot know whether this project keeps those directories in
-version control, so name them before you write them rather than after. Then run
-`npx skills add CopilotKit/CopilotKit/skills -y` to install the
-project-scoped CopilotKit Skills.
-<!-- sandboxed-harness -->
-It needs the network, so in a sandbox request escalation for it on its first run.
-<!-- /sandboxed-harness -->
-Record that the proof ran the install because the implementation did not.
-
-Do not register an MCP server: the Skills read the CopilotKit documentation without one.
-
-Check whether the install succeeded and record what you found. Record the command result.
-Report the Skills result separately from the proof result. A tool error does not change the
-proof result: this journey proved or it did not, whatever the install did.
+```text
+npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase subagent-returned --brief prove-round-trip --result <ok|failed>
+```
 
-## Step 10 -- Return the result
+The Status line of your result decides the value. Pass `ok` only for `Status: passed`.
+Pass `failed` for `Status: failed` or `Status: blocked`. If your harness refuses this command, say so in your result and return
+anyway: the main coding agent records it.
 
 Start with `Status: passed`, `Status: failed`, or `Status: blocked`.
 Use `Status: passed` when the proof attempt completed with `performed`,

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

@@ -36,17 +36,17 @@ Before you show the best-effort plan, require this complete packet:
 Before you end your turn to wait for the developer, report the pause:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
+npx --prefer-offline --yes copilotkit@4.29.0 onboard checkpoint --phase awaiting-plan-approval
 ```
 
 After the developer approves the best-effort plan, run
-`npx --prefer-offline --yes copilotkit@4.27.0 onboard read fallback/best-effort`.
+`npx --prefer-offline --yes copilotkit@4.29.0 onboard read fallback/best-effort`.
 
 Send one short report. The friction command follows the telemetry setting the developer
 already chose, so it needs no separate question.
 
 ```text
-npx --prefer-offline --yes copilotkit@4.27.0 onboard friction --phase stop --category <slug> --message "<sentences>"
+npx --prefer-offline --yes copilotkit@4.29.0 onboard friction --phase stop --category <slug> --message "<sentences>"
 ```
 
 `--message` takes one or two sentences: the step you stopped at and what stopped it.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "copilotkit",
-  "version": "4.27.0",
+  "version": "4.29.0",
   "type": "module",
   "engines": {
     "node": ">=20.9.0"

package/release/release-tool.js

@@ -14984,7 +14984,7 @@ init_define_CLI_LOCAL_EVALUATION_SUPPORT();
 
 // apps/cli/src/config.ts
 function getTemplateRef() {
-  return true ? "3cddb360660503325b24564820c78a2ad7ee1843" : "main";
+  return true ? "c616389550105d5a96d74501f77c6921aa79ecee" : "main";
 }
 
 // apps/cli/src/services/agentcore-config.ts
@@ -15182,6 +15182,13 @@ var TELEMETRY_ERROR_CODES = {
    * tell "the caller guessed a slug" from a malformed request.
    */
   PROJECT_NOT_FOUND: "PROJECT_NOT_FOUND",
+  /**
+   * `init --create` named a project the active organization already has.
+   * Distinct from {@link TELEMETRY_ERROR_CODES.PROJECT_NOT_FOUND}, which it was
+   * tagged as, so the dashboard counted a taken name as a missing project
+   * (PE-784).
+   */
+  PROJECT_NAME_TAKEN: "PROJECT_NAME_TAKEN",
   /**
    * `project select` persisted the record and the key-provisioning call did
    * not succeed. Buckets as `network` because that is what it almost always