copilotkit 4.16.0 → 4.18.0

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

@@ -3,15 +3,26 @@
 Implement every step of the approved plan in plan order, and run the full validation list.
 Do not repeat the full repository inspection.
 
-Do not change a protected path. Do not delete, move, or rename one either, whatever the
-plan says: a protected path that is gone fails the audit and no command clears that.
-Do not change a path that overlaps a protected path. Paths overlap when they are equal or
+Do not change a protected path unless it is on the authorized list the main coding agent
+gave you. That list comes from the CLI, which recorded the developer's consent for each
+path on it. An authorization covers that exact path only, not an ancestor directory and not
+a file inside it. Never delete, move, or rename a protected path, authorized or not,
+whatever the plan says: a protected path that is gone fails the audit and no command
+clears that. Do not change a path that overlaps a protected path. An authorized path
+itself is the one exception. 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`.
 
-Change only the files and directories the approved plan names as changeable. If the work
-requires a file the plan does not name, return the blocker and end your turn. Do not run a
-repository-wide formatter.
+Change only the files and directories the approved plan names as changeable. A path on
+the authorized list counts as one the plan names, and so does a path the main coding agent
+adds to your handoff as one the developer approved. Two kinds of file outside that list are
+departures, not blockers. The first is a file that has the same role as a planned file at a
+different path, for example `app/page.tsx` for a planned `src/app/page.tsx`. The second is
+the documentation file this prompt tells you to write. Mark each departure in Files
+changed: the path the plan named, if any, the path you changed, and why. Neither kind
+covers a protected path. If the work requires any other file the plan does not name, return
+`Status: blocked`, name the file and why the work needs it under Blockers, 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
 directory the main coding agent named. Never work in a separate worktree, a branch
@@ -21,10 +32,12 @@ completion step verifies that the changed files exist in this project, so work l
 another tree ends the run with nothing in the developer's hands.
 
 Before validation, read the protected path list. Inspect the current changed and untracked
-paths. Keep protected paths out of the run path set. Compare every changed path with the
+paths. Keep protected paths out of the run path set, except the authorized paths, which
+belong in it. Compare every changed path with the
 paths the plan named. Here, a changed path means one in the run path set. If a changed path
-is outside them, return `Status: blocked` before validation. Run the approved validation
-commands one at a time. Fix validation and proof defects only in the paths the plan named.
+is outside them and is not a departure you marked, return `Status: blocked` before
+validation. Run the approved validation commands one at a time. Fix validation and proof
+defects only in the paths the plan named and the departures you marked.
 
 Use only the approved plan and the selected documentation URLs. Follow the documentation
 policy the main coding agent gives you before you change the project.
@@ -61,7 +74,7 @@ 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
+do not overlap a protected path. A path on the authorized list is the one exception. 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.
 
@@ -83,7 +96,8 @@ change, and the check that asked for it. Do not edit the agent's prompt to make
 component render.
 
 An existing `README.md` is the developer's, not this run's. Leave it exactly as you found
-it: not the title, not a section, not a line. Where this run has documentation to write,
+it: not the title, not a section, not a line. The one exception is a README on the
+authorized list. Where this run has documentation to write,
 write it to a new file and name that file when you report the result. On an empty project
 the README is the whole of the brief -- the only place the developer said what they
 wanted, and the thing they read this run's result against -- so the rule binds hardest

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

@@ -7,15 +7,22 @@ Work only on the packet you were assigned. Inspect the repository without changi
 Run this first, from the target project directory:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 onboard inspect --json
+npx --prefer-offline --yes copilotkit@4.18.0 onboard inspect --json
 ```
 
 It answers the deterministic half of both packets exactly, from the same code
 `copilotkit verify` uses: the project record by presence, and, for each app or runtime
 directory on its own, the env files, which variable carries the Intelligence key and which
 file it came from, whether that directory's own process can load it, the package manager
-its lockfile proves, the port it declares, and the exact installed version of every
-`@copilotkit/*` dependency. It reads only and prints no secret value.
+its lockfile proves, the port it declares, the exact installed version of every
+`@copilotkit/*` dependency, every provider base URL its process will read, and the
+module resolution its `tsconfig.json` sets, read through the `extends` chain. It reads
+only and prints no secret value.
+
+Report each `providerEndpoints` entry with the variable, its origin, and where it came
+from. A `null` `source` means the process environment supplied it. A coding agent's shell
+passes that value on to every dev server it starts, so it decides where the model calls
+go before any project file does. Carry its `warning` as it came back.
 
 Carry those readings into your findings as they came back. Do not work one of them out
 again by reading files. The directory that owns `.env` is the hard case and the CLI holds
@@ -43,7 +50,7 @@ Find evidence for:
 Return the initial changed and untracked paths as paths only. Do not return their
 contents. Do not retain a before-state for them. The CLI captures the baseline that the
 protected-path audit compares against, so nothing later in the run depends on this
-subagent still existing, and a path that can hold secrets is captured as a digest you
+subagent still holding its state, and a path that can hold secrets is captured as a digest you
 never read.
 
 Take the target app or runtime directory from the CLI packet rather than working it out
@@ -53,13 +60,20 @@ reading of the files will not reproduce.
 ## Environment evidence packet
 
 - names of required credential variables, beyond the Intelligence key the CLI reported
-- retain the `.env` modification time for a later comparison without returning it
+- the `.env` modification time, or that no `.env` exists, for a later comparison. It is a
+  timestamp, not a value from the file
 - required toolchains and their installed versions
 - whether each port the CLI reported as declared is free
 - whether the runtime constructor uses a `runner` option, an `intelligence` option, or
   neither can be proved from project files
 - package compatibility risks, and whether any `@copilotkit/*` version the CLI reported is
   below 1.70.0
+- the `tsconfig.json` change each app needs, from `typescript.migration`: its file and each
+  change, as they came back. The change lets CopilotKit subpath imports such as
+  `@copilotkit/runtime/v2` type-check. A `null` migration means that no change is needed.
+  Where `typescript.status` is `unreadable` or `typescript.unresolvedExtends` is not
+  empty, read that app's `tsconfig.json` chain and report its `moduleResolution` and
+  `module` values, or report them as unproved
 
 Key every environment finding by its app or runtime directory. Do not combine findings
 from different directories. The CLI packet keys its own readings the same way.
@@ -85,6 +99,7 @@ access or an environment limit prevents the inspection.
 Return one row for each assigned item with its status, evidence path, and a short finding.
 Use only `proved`, `absent`, or `unproved` for the status. State each absent or unproved item.
 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
+checks, return only paths, presence checks, missing field names, and the one `.env`
+modification time named above. Do not read a file
 outside the project directory. Do not run or return an onboarding command other than
 `onboard inspect`. End your turn after returning the findings to the main coding agent.

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

@@ -32,7 +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 --prefer-offline --yes copilotkit@4.16.0 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
+   `npx --prefer-offline --yes copilotkit@4.18.0 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
@@ -46,9 +46,10 @@ asked for one, which is a different thing from a server registered against the c
 Where the recorded control is `unavailable`, record predicate 6 as skipped, with that as the
 reason, and prove the rest.
 
-Classify the state as `both-oss` when predicates 1 to 5 are all true. Predicate 5 proves the
-CopilotKit round trip from a shell, so those five settle the starting state on their own.
-Predicate 6 adds the user-visible surface on top of a state already proved: record it as
+Classify the state as `both-oss` when predicates 1 to 5 are all true and predicate 6 did
+not fail. Predicate 5 proves the
+CopilotKit round trip from a shell, so a skipped predicate 6 leaves those five to settle
+the starting state. Predicate 6 adds the user-visible surface on top of a state already proved: record it as
 passed, failed, or skipped, and do not withhold `both-oss` for a skip. A failed predicate 6
 on an available surface is a baseline failure and is not a skip. Return each predicate and
 its secret-safe evidence.

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

@@ -5,10 +5,16 @@ policy the main coding agent gives you before you start.
 
 During Steps 1 through 8, do not edit source files, configuration files, dependencies, or
 tracked files.
-You can make only operational repairs to project-owned processes, ports, and request options.
+You can make only operational repairs to project-owned processes, ports, and request options,
+and the credential write that Step 4 names for `api_key_loadable_by_app`.
 Do not write a path that overlaps a protected path. If a required proof or tool path
 overlaps one, return `Status: blocked` before writing it.
 
+One CLI command is the exception to both rules. The Step 2 `onboard runtime-url` command
+can write `.copilotkit/project.json` even when that path is protected. It moves the
+protected-path baseline with its own write, and it refuses a record that changed since the
+baseline. Never edit that file any other way.
+
 The existing agent's behavior is outside every step of this proof. It is four things: the
 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
@@ -24,8 +30,13 @@ different sequence of your own, and do not drop a step because an earlier one lo
 convincing. Step 6 has a web form and a React Native form: run the one that matches this
 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 Steps 1 through 5 up to and including the
+`verify --round-trip` command, then go to Step 10. Skip Steps 5a through 9, 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 Step 2 through Step 7
-again. The repair changed tracked files and restarted processes, so the wiring, the agent
+again, or through the Step 5 `verify --round-trip` command for a cloned-starter run. The repair changed tracked files and restarted processes, so the wiring, the agent
 identity, and both preconditions are stale. Step 1 is the exception, and it is carried
 rather than derived a second time. Compare the Step 5a and Step 5b results against the
 failed attempt's before you drive the surface. A repair that leaves the failed precondition
@@ -117,6 +128,22 @@ A zero exit means the server answered. Any other exit means that it did not answ
 seconds. A server that never answered has written the reason to its own output, and
 reading that output is faster than starting it again.
 
+When the server that serves the runtime answers, record the URL it serves on. Read the port
+from that server's own output or its listener, not from the plan. A dev server whose port
+is taken moves to the next free one without asking. Where the runtime runs as a process of
+its own, this is the runtime's port, not the frontend's.
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard runtime-url --url <runtime-url>
+```
+
+`<runtime-url>` is the Step 1 runtime URL with its port replaced by the port that server
+bound. Keep its host and its mount path unchanged.
+
+The command writes `runtimeUrl` into `.copilotkit/project.json` and changes nothing else. It
+mints no key and does not touch `.env`. Step 4 reads that record, so `verify` probes the
+server you started. Run the command again after any restart that binds another port.
+
 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
 read the round trip. A check run against a frontend whose agent was stopped with it reports
@@ -157,10 +184,10 @@ 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 --prefer-offline --yes copilotkit@4.16.0 verify --json`. It reads the port from this project, so a
+`npx --prefer-offline --yes copilotkit@4.18.0 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
+`runtimeUrlSource` of `default` means nothing in the project named a port, so the Step 2
+record is missing. Run the Step 2 `onboard runtime-url` command, then run `verify` again. Read the individual checks rather than
 the summary alone: a check reported `undetermined` did not run, and that is not a pass.
 Repair a failed check only within the limits above. Otherwise, return the check and its
 evidence before the browser.
@@ -191,7 +218,7 @@ 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 --prefer-offline --yes copilotkit@4.16.0 verify --frontend-url <that url> --json`. The
+`npx --prefer-offline --yes copilotkit@4.18.0 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
@@ -199,7 +226,7 @@ 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 --prefer-offline --yes copilotkit@4.16.0 verify --round-trip --json`. It sends one request through
+Run `npx --prefer-offline --yes copilotkit@4.18.0 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
@@ -212,7 +239,7 @@ Where this run settled a Learning Container, add the flag to the call above rath
 running a second round trip:
 
 ```text
-npx --prefer-offline --yes copilotkit@4.16.0 verify --round-trip --expect-learning-container <container id> --json
+npx --prefer-offline --yes copilotkit@4.18.0 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
@@ -246,7 +273,7 @@ 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 --prefer-offline --yes copilotkit@4.16.0 onboard env-staleness
+npx --prefer-offline --yes copilotkit@4.18.0 onboard env-staleness
 ```
 
 A `stale` line names the env file and how long after launch it was written. Report that,
@@ -256,6 +283,21 @@ process and never its owner, and one project's dev script often serves the agent
 frontend together. Editing a file to answer a 401 that a restart clears changes the project
 for a fault it does not have.
 
+Where the runtime answers with a 404 from the model provider, check the base URLs the
+processes inherited before you change anything. A coding agent's shell passes its own
+environment on to every process it starts, so a provider base URL exported for the agent
+reaches the dev servers. Run this from the target app directory:
+
+```text
+npx --prefer-offline --yes copilotkit@4.18.0 onboard inspect --json
+```
+
+Read `providerEndpoints` for the app directory. An entry with a `null` `source` came from
+the process environment rather than from a project file. A `warning` names why that value
+fails. Report the variable, where it came from, and the warning, and say that the server
+has to start from an environment without that value before the 404 means anything. Do not
+edit a project file to answer it: the value lives in the shell, not in the project.
+
 ### Step 5a -- Prove that the page's data reaches the model
 
 `verify --round-trip` sends `context: []` and asks a question that needs no context. It
@@ -269,13 +311,22 @@ entries this project's frontend publishes, from its own context call. Read the t
 declarations it registers as well, and carry both the way the page carries them, so that
 the agent sees the request the browser sends rather than a thinner one. Send the same run
 body twice, to `<runtime>/agent/<agent id>/run`: once carrying the context entries the page
-publishes, and once carrying `context: []`. Use the step 1 request both times. Record the
-streamed events from each, and name both capture paths.
-
-Read the two answers against each other. The run carrying the page's context has to name
-the project's own records. The run carrying an empty context has to say the page sent
-nothing. Two answers that describe the same record mean the context changed nothing, and
-the page's data is not reaching the model.
+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.
+
+For the changed run, pick one record the step 1 request matches. Add a marker to a text
+field that the answer repeats, such as its title or name:
+` [probe-<8 random hex characters>]`. Choose a new marker for each run, record it, and
+change nothing else. Do not remove the entry or send `context: []` instead. The page always
+sends its entries. A model with a request about records, a tool that needs them, and
+nothing to copy invents records. That failure belongs to the probe, not to the integration.
+
+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
+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.
 
 Return the cause and both captures on a failed comparison. Do not open a browser on a
 failed comparison, and do not edit the project here.
@@ -318,13 +369,14 @@ holds. Streamed text alone is not this step's outcome, whatever it says.
 This is the step that covers realtime delivery, the frontend provider being wired to this
 runtime, and the component actually rendering, and no command-line check reaches any of
 them. It is not optional polish: a run that skips it has proven the agent and not the
-journey, and such a run ends as blocked rather than complete.
+journey, and such a run ends as blocked rather than complete. The cloned-starter skip is
+the one exception, and it completes the run.
 
 For a recorded `both-oss` starting state, this step has no component to render. Send the
 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@4.16.0 verify --round-trip`, which reads the
+that thread with `npx --prefer-offline --yes copilotkit@4.18.0 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
@@ -352,7 +404,7 @@ 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 --prefer-offline --yes copilotkit@4.16.0 verify --frontend-url <the url you opened> --json`
+   `npx --prefer-offline --yes copilotkit@4.18.0 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.
@@ -377,8 +429,9 @@ request never exercises. Drive it with the browser control step 6 named.
    the answer from, and what that element showed.
 
 Report exactly one of `performed`, `skipped-no-browser-tool`, `skipped-cloned-starter`, or
-`failed` for a web frontend. Report `skipped-cloned-starter` when this prompt told you to
-open no browser because the run cloned a starter.
+`failed` for a web frontend. Report `skipped-cloned-starter` when the main coding agent told
+you to open no browser because the run cloned a starter. The cloned-starter exception above
+Step 1 says which steps to run.
 
 ### Step 6b -- React Native
 
@@ -495,8 +548,9 @@ whatever these two tools did.
 
 Start with `Status: passed`, `Status: failed`, or `Status: blocked`.
 Use `Status: passed` when the proof attempt completed with `performed`,
-`skipped-no-browser-tool`, or `skipped-no-device`. The parent records a skip through the
-standard blocked completion route. Use `Status: failed` for a failed proof step. Use
+`skipped-no-browser-tool`, `skipped-no-device`, or `skipped-cloned-starter`. The parent
+records a skip through the standard completion route, which ends every skip but
+`skipped-cloned-starter` as blocked. Use `Status: failed` for a failed proof step. Use
 `Status: blocked` when a safety or access limit stops the attempt before a surface outcome.
 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

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 --prefer-offline --yes copilotkit@4.16.0 onboard read fallback/best-effort`.
+`npx --prefer-offline --yes copilotkit@4.18.0 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.
+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@4.16.0 onboard friction --phase stop --category <slug> --message "<sentences>"
+npx --prefer-offline --yes copilotkit@4.18.0 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": "4.16.0",
+  "version": "4.18.0",
   "type": "module",
   "engines": {
     "node": ">=20.9.0"
@@ -16,9 +16,5 @@
   "optionalDependencies": {
     "@microsoft/teams.cli": "3.0.3"
   },
-  "dependencies": {
-    "@mastra/core": "1.48.0",
-    "@mastra/libsql": "1.14.3"
-  },
   "license": "SEE LICENSE IN LICENSE"
 }