copilotkit 4.9.1 → 4.9.4

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (45) hide show
  1. package/cli-build-info.json +8 -8
  2. package/index.js +151 -21
  3. package/onboarding/index.json +11 -0
  4. package/onboarding/prompts/authenticate/start.md +83 -32
  5. package/onboarding/prompts/credentials/finalize-plan.md +51 -33
  6. package/onboarding/prompts/credentials/plan.md +37 -25
  7. package/onboarding/prompts/fallback/best-effort.md +22 -11
  8. package/onboarding/prompts/framework/ag2.md +4 -15
  9. package/onboarding/prompts/framework/agno.md +4 -15
  10. package/onboarding/prompts/framework/built-in.md +4 -14
  11. package/onboarding/prompts/framework/claude-sdk-python.md +4 -14
  12. package/onboarding/prompts/framework/claude-sdk-typescript.md +4 -14
  13. package/onboarding/prompts/framework/crewai-flows.md +11 -23
  14. package/onboarding/prompts/framework/deep-agents.md +4 -15
  15. package/onboarding/prompts/framework/google-adk.md +3 -15
  16. package/onboarding/prompts/framework/langgraph-fastapi.md +3 -15
  17. package/onboarding/prompts/framework/langgraph-python.md +3 -15
  18. package/onboarding/prompts/framework/langgraph-typescript.md +3 -15
  19. package/onboarding/prompts/framework/llamaindex.md +4 -15
  20. package/onboarding/prompts/framework/mastra.md +3 -15
  21. package/onboarding/prompts/framework/ms-agent-dotnet.md +18 -49
  22. package/onboarding/prompts/framework/ms-agent-harness-dotnet.md +20 -30
  23. package/onboarding/prompts/framework/ms-agent-python.md +3 -15
  24. package/onboarding/prompts/framework/pydantic-ai.md +4 -14
  25. package/onboarding/prompts/framework/strands-python.md +4 -14
  26. package/onboarding/prompts/framework/strands-typescript.md +4 -14
  27. package/onboarding/prompts/frontend/angular.md +13 -18
  28. package/onboarding/prompts/frontend/nextjs.md +20 -15
  29. package/onboarding/prompts/frontend/plan.md +9 -14
  30. package/onboarding/prompts/frontend/react-native.md +7 -15
  31. package/onboarding/prompts/frontend/react-spa.md +5 -15
  32. package/onboarding/prompts/frontend/vue.md +8 -15
  33. package/onboarding/prompts/implementation/build-and-validate.md +22 -13
  34. package/onboarding/prompts/proof/complete.md +32 -5
  35. package/onboarding/prompts/proof/oss-baseline.md +3 -3
  36. package/onboarding/prompts/proof/round-trip.md +197 -72
  37. package/onboarding/prompts/starter/clone.md +67 -0
  38. package/onboarding/prompts/subagent/create-plan.md +26 -15
  39. package/onboarding/prompts/subagent/implement-and-validate.md +19 -10
  40. package/onboarding/prompts/subagent/inspect-repository.md +19 -7
  41. package/onboarding/prompts/subagent/prove-oss-baseline.md +1 -1
  42. package/onboarding/prompts/subagent/prove-round-trip.md +176 -68
  43. package/onboarding/prompts/unsupported/no-validated-path.md +2 -2
  44. package/package.json +1 -1
  45. package/release/release-tool.js +15 -1
@@ -5,9 +5,9 @@ that the repository does not show. Do not change application code in this phase.
5
5
 
6
6
  Use a gentle wizard. Ask one short question at a time. Do not combine separate choices in
7
7
  one question. Put the recommendation first, give its evidence in one sentence, and keep
8
- the alternatives short. When the frontend is unknown, ask only whether to use the
9
- recommended frontend. If the developer declines it, ask one follow-up question that lists
10
- the valid frontend choices. Do not ask about the model or project in this step.
8
+ the alternatives short. When the frontend is unknown, use this rule: Ask one frontend
9
+ question that lists the recommendation and valid choices. Do not ask a yes-or-no question
10
+ first. Do not ask about the model or project in this step.
11
11
 
12
12
  If the project has a frontend, preserve it and use the matching route below. If the project
13
13
  needs a frontend, show the valid choices and one recommendation based on repository
@@ -22,18 +22,13 @@ CopilotKit runtime lives: Next.js hosts it in a route handler, Angular in its SS
22
22
  server, and Vue 3, React SPA and React Native reach a runtime that runs as its own
23
23
  process.
24
24
 
25
- A fetch tool that refuses a URL, or fails to reach it, reports a limit of the tool and
26
- not a fact about the page. Retrieve the same URL a second way before you judge it. Run
27
- `curl -fsSL <url>`, or read the same page without the `.md` suffix. Treat a page as
28
- unavailable only after a second method also fails.
29
-
30
25
  Use exactly one matching internal route:
31
26
 
32
- 1. React SPA: `npx --yes copilotkit@4.9.1 onboard read frontend/react-spa`
33
- 2. Next.js: `npx --yes copilotkit@4.9.1 onboard read frontend/nextjs`
34
- 3. Angular: `npx --yes copilotkit@4.9.1 onboard read frontend/angular`
35
- 4. Vue 3: `npx --yes copilotkit@4.9.1 onboard read frontend/vue`
36
- 5. React Native: `npx --yes copilotkit@4.9.1 onboard read frontend/react-native`
27
+ 1. React SPA: `npx --yes copilotkit@4.9.4 onboard read frontend/react-spa`
28
+ 2. Next.js: `npx --yes copilotkit@4.9.4 onboard read frontend/nextjs`
29
+ 3. Angular: `npx --yes copilotkit@4.9.4 onboard read frontend/angular`
30
+ 4. Vue 3: `npx --yes copilotkit@4.9.4 onboard read frontend/vue`
31
+ 5. React Native: `npx --yes copilotkit@4.9.4 onboard read frontend/react-native`
37
32
 
38
33
  If no listed frontend fits, run
39
- `npx --yes copilotkit@4.9.1 onboard read unsupported/no-validated-path`.
34
+ `npx --yes copilotkit@4.9.4 onboard read unsupported/no-validated-path`.
@@ -4,21 +4,13 @@ Preserve an existing React Native frontend. Use the selected page for a new fron
4
4
 
5
5
  ## Documentation
6
6
 
7
- - Credentials and plan: `Not applicable`
8
- - Implementation and validation: https://docs.copilotkit.ai/react-native.md
9
- - Proof: https://docs.copilotkit.ai/react-native.md
7
+ - https://docs.copilotkit.ai/react-native.md
8
+ - https://docs.copilotkit.ai/troubleshooting/event-inspector.md
10
9
 
11
- Fetch the selected documentation page. Record React Native as the selected frontend and
12
- keep this URL. Do not use remembered CopilotKit instructions.
10
+ Use the Event Inspector page for proof.
13
11
 
14
- A fetch tool that refuses a URL, or fails to reach it, reports a limit of the tool and
15
- not a fact about the page. Retrieve the same URL a second way before you judge it. Run
16
- `curl -fsSL <url>`, or read the same page without the `.md` suffix. Treat a page as
17
- unavailable only after a second method also fails.
12
+ If the pages support the selection, record React Native and these URLs. Then run
13
+ `npx --yes copilotkit@4.9.4 onboard read credentials/finalize-plan`.
18
14
 
19
- If the page supports the selection, run
20
- `npx --yes copilotkit@4.9.1 onboard read credentials/finalize-plan`.
21
-
22
- If a second method also fails, or the page that loads does not support the selection,
23
- run
24
- `npx --yes copilotkit@4.9.1 onboard read unsupported/no-validated-path`.
15
+ If the documentation does not support the selection, run
16
+ `npx --yes copilotkit@4.9.4 onboard read unsupported/no-validated-path`.
@@ -8,20 +8,10 @@ not move the agent into it.
8
8
 
9
9
  ## Documentation
10
10
 
11
- - Credentials and plan: `Not applicable`
12
- - Implementation and validation: https://docs.copilotkit.ai/react-spa.md
13
- - Proof: https://docs.copilotkit.ai/react-spa.md
11
+ - https://docs.copilotkit.ai/react-spa.md
14
12
 
15
- Fetch the selected documentation page. Record React SPA as the selected frontend and
16
- keep this URL. Do not use remembered CopilotKit instructions.
13
+ If the page supports the selection, record React SPA and this URL. Then run
14
+ `npx --yes copilotkit@4.9.4 onboard read credentials/finalize-plan`.
17
15
 
18
- A fetch tool that refuses a URL, or fails to reach it, reports a limit of the tool and
19
- not a fact about the page. Retrieve the same URL a second way before you judge it. Run
20
- `curl -fsSL <url>`, or read the same page without the `.md` suffix. Treat a page as
21
- unavailable only after a second method also fails.
22
-
23
- If the page supports the selection, run
24
- `npx --yes copilotkit@4.9.1 onboard read credentials/finalize-plan`.
25
-
26
- If a second method also fails, or a page that loads does not support the selection, run
27
- `npx --yes copilotkit@4.9.1 onboard read unsupported/no-validated-path`.
16
+ If the documentation does not support the selection, run
17
+ `npx --yes copilotkit@4.9.4 onboard read unsupported/no-validated-path`.
@@ -4,21 +4,14 @@ Preserve an existing Vue 3 frontend. Use the selected page for a new frontend.
4
4
 
5
5
  ## Documentation
6
6
 
7
- - Credentials and plan: `Not applicable`
8
- - Implementation and validation: https://docs.copilotkit.ai/vue.md
9
- - Proof: https://docs.copilotkit.ai/vue.md
7
+ - https://docs.copilotkit.ai/vue.md
8
+ - https://docs.copilotkit.ai/reference/vue/components/CopilotKitProvider.md
9
+ - https://docs.copilotkit.ai/reference/vue/hooks/useAgentContext.md
10
10
 
11
- Fetch the selected documentation page. Record Vue 3 as the selected frontend and keep
12
- this URL. Do not use remembered CopilotKit instructions.
11
+ Use the component page for the provider setup. Use the hook page for frontend context.
13
12
 
14
- A fetch tool that refuses a URL, or fails to reach it, reports a limit of the tool and
15
- not a fact about the page. Retrieve the same URL a second way before you judge it. Run
16
- `curl -fsSL <url>`, or read the same page without the `.md` suffix. Treat a page as
17
- unavailable only after a second method also fails.
13
+ If the pages support the selection, record Vue 3 and these URLs. Then run
14
+ `npx --yes copilotkit@4.9.4 onboard read credentials/finalize-plan`.
18
15
 
19
- If the page supports the selection, run
20
- `npx --yes copilotkit@4.9.1 onboard read credentials/finalize-plan`.
21
-
22
- If a second method also fails, or the page that loads does not support the selection,
23
- run
24
- `npx --yes copilotkit@4.9.1 onboard read unsupported/no-validated-path`.
16
+ If the documentation does not support the selection, run
17
+ `npx --yes copilotkit@4.9.4 onboard read unsupported/no-validated-path`.
@@ -4,11 +4,11 @@ Do not implement the plan yourself. Spawn one implementation subagent.
4
4
 
5
5
  Give the subagent the full text of the implementation brief at the end of this prompt, the
6
6
  approved plan, selected framework, frontend, model, repository findings, and selected
7
- documentation URLs.
7
+ documentation URLs. Give it the documentation policy recorded during framework selection.
8
8
  Wait for the subagent to finish.
9
9
 
10
10
  If all implementation and validation steps pass, run
11
- `npx --yes copilotkit@4.9.1 onboard read proof/round-trip`.
11
+ `npx --yes copilotkit@4.9.4 onboard read proof/round-trip`.
12
12
 
13
13
  If a validation command fails, decide which kind of failure it is before you route.
14
14
 
@@ -20,7 +20,7 @@ Route out only when the failure is not yours to fix: the failure is in code this
20
20
  not write, or the fix requires changing the developer's existing agent or frontend,
21
21
  or the same command still fails after three repair attempts, or the documentation does not
22
22
  support the plan. In those cases run
23
- `npx --yes copilotkit@4.9.1 onboard read unsupported/no-validated-path`.
23
+ `npx --yes copilotkit@4.9.4 onboard read unsupported/no-validated-path`.
24
24
 
25
25
  ## Implementation subagent brief
26
26
 
@@ -30,14 +30,8 @@ Everything below the rule is the subagent's prompt. Give it verbatim.
30
30
 
31
31
  # Implement and validate the approved plan
32
32
 
33
- Use only the approved plan and the selected documentation URLs. Fetch every URL in one
34
- step, before you change the project, rather than one after another.
35
- Do not use remembered CopilotKit instructions.
36
-
37
- A fetch tool that refuses a URL, or fails to reach it, reports a limit of the tool and
38
- not a fact about the page. Retrieve the same URL a second way before you judge it. Run
39
- `curl -fsSL <url>`, or read the same page without the `.md` suffix. Report a
40
- documentation gap only after a second method also fails.
33
+ Use only the approved plan and the selected documentation URLs. Follow the documentation
34
+ policy the main coding agent gives you before you change the project.
41
35
 
42
36
  Add only the props, options, and imports that appear in the fetched documentation. A
43
37
  remembered API from an earlier CopilotKit version will fail type checking against this
@@ -57,8 +51,23 @@ for.
57
51
 
58
52
  For a recorded `both-oss` baseline, preserve the existing agent, frontend, CopilotKit
59
53
  integration, user-visible request, and runtime behavior. Do not replace the existing
60
- persistence. Change only the approved project selection and Intelligence runtime wiring.
61
- Run the recorded baseline checks after the change and report any regression.
54
+ persistence. Change only the approved project selection, the approved CopilotKit
55
+ dependency upgrade, and the Intelligence runtime wiring.
56
+ Run the recorded baseline checks again after the Intelligence wiring and report any
57
+ regression.
58
+
59
+ Apply the planned CopilotKit dependency upgrade before you wire Intelligence, as its own
60
+ step, and record each version it changed. Then re-run the recorded baseline checks. A
61
+ regression at this point can only be the upgrade, which is why it is checked here rather
62
+ than after the wiring.
63
+
64
+ If the baseline regresses, restore the manifest and lockfile to their recorded state,
65
+ leave Intelligence unwired, and report the regression with the failing check. A
66
+ half-upgraded project with no working chat is worse than the one this run was given, and
67
+ finishing the wiring on top of a broken baseline hides which change broke it.
68
+
69
+ Report each `@copilotkit/*` version before and after the upgrade. Where the plan named no
70
+ dependency change, say that the installed versions already met the floor.
62
71
 
63
72
  When the documentation creates the frontend with the framework's own scaffolder,
64
73
  run that scaffolder rather than hand-authoring what it emits.
@@ -36,9 +36,19 @@ The handoff must include:
36
36
 
37
37
  - The URL of the running app.
38
38
  - The command that starts the app in the future.
39
- - How to use the CopilotKit Inspector.
39
+ - The debugging surface this journey's frontend can reach, named below.
40
40
  - How to use https://intelligence.copilotkit.ai to manage the Intelligence installation.
41
41
  - The process IDs and stop commands for the running agent and frontend.
42
+ - The `@copilotkit/*` versions this conversion changed, and what they were before.
43
+
44
+ Name the debugging surface this journey's frontend can reach, rather than the one the rest
45
+ of the documentation leads with. For a web frontend it is the CopilotKit Inspector. For
46
+ React Native there is no Inspector: it is a browser overlay built on a DOM custom element,
47
+ and `@copilotkit/react-native` does not ship it. Give a mobile developer
48
+ `npx --yes copilotkit@4.9.4 verify --round-trip`, the runtime's own log, the AG-UI
49
+ Event Inspector in the CopilotKit VS Code extension, and the Intelligence thread view
50
+ instead. Naming the Inspector to a developer who cannot open it costs them the time it
51
+ takes to conclude their own wiring is broken.
42
52
 
43
53
  State that the servers remain running after proof.
44
54
 
@@ -47,7 +57,7 @@ the friction commands without another developer question. The CLI telemetry gate
47
57
  whether the report is sent.
48
58
 
49
59
  ```text
50
- npx --yes copilotkit@4.9.1 onboard friction --category <slug> --cost-seconds <seconds>
60
+ npx --yes copilotkit@4.9.4 onboard friction --category <slug> --cost-seconds <seconds>
51
61
  ```
52
62
 
53
63
  Write one or two sentences on the command's standard input. Pick one category from
@@ -64,14 +74,14 @@ Tell the developer when you send a friction report. Do not quote or summarize th
64
74
  unless the developer asks. If the CLI says that telemetry is disabled or unavailable,
65
75
  state that the report was not sent and continue without another question.
66
76
 
67
- When the evidence is gathered, run `npx --yes copilotkit@4.9.1 onboard complete`, carrying
77
+ When the evidence is gathered, run `npx --yes copilotkit@4.9.4 onboard complete`, carrying
68
78
  the surface-check outcome the proof subagent returned. Pass exactly one flag, and pass the
69
79
  one that matches this journey's surface.
70
80
 
71
81
  For a web frontend -- React SPA, Next.js, Angular, Vue:
72
82
 
73
83
  ```text
74
- npx --yes copilotkit@4.9.1 onboard complete --visual-check <outcome>
84
+ npx --yes copilotkit@4.9.4 onboard complete --visual-check <outcome>
75
85
  ```
76
86
 
77
87
  The outcome is one of `performed`, `skipped-no-browser-tool`, or `failed`.
@@ -79,7 +89,7 @@ The outcome is one of `performed`, `skipped-no-browser-tool`, or `failed`.
79
89
  For React Native:
80
90
 
81
91
  ```text
82
- npx --yes copilotkit@4.9.1 onboard complete --device-check <outcome>
92
+ npx --yes copilotkit@4.9.4 onboard complete --device-check <outcome>
83
93
  ```
84
94
 
85
95
  The outcome is one of `performed`, `skipped-no-device`, or `failed`.
@@ -92,3 +102,20 @@ Pass the outcome you were given rather than the one you wanted. Anything but `pe
92
102
  prints what the missing check leaves unverified and ends this run as blocked. That output
93
103
  is the developer's finding, so carry it into the summary rather than restating it as a
94
104
  smaller caveat.
105
+
106
+ If the round trip proved and something after it still blocked this run, add `--blocked-by`
107
+ to the same command:
108
+
109
+ ```text
110
+ npx --yes copilotkit@4.9.4 onboard complete --visual-check performed --blocked-by <cause>
111
+ ```
112
+
113
+ The cause is one of `hosted-dashboard` for a managed dashboard that did not load or refused
114
+ a sign-in, `inspector` for a debugging surface that did not open, `plan-excluded-capability`
115
+ for a capability the approved plan had already excluded for this framework, and `other` for
116
+ anything else. Pick `other` rather than leaving the flag off. The command ends the run as
117
+ blocked and prints what the blocker leaves unverified.
118
+
119
+ This is the flag for a journey that worked. It is not a way to report an unsupported path,
120
+ and a blocked run here is still owed the full handoff above: the URL, the start command,
121
+ the process IDs, and the versions this conversion changed.
@@ -10,11 +10,11 @@ processes and their ignored runtime files is allowed.
10
10
 
11
11
  If the subagent proves the `both-oss` predicate, keep its evidence with the plan. If it
12
12
  proves another supported starting state, record that state. In either case, run
13
- `npx --yes copilotkit@4.9.1 onboard read credentials/plan`.
13
+ `npx --yes copilotkit@4.9.4 onboard read credentials/plan`.
14
14
 
15
15
  If it cannot identify the running process safely, exposes a secret, or finds a baseline
16
16
  failure that cannot be classified, run
17
- `npx --yes copilotkit@4.9.1 onboard read unsupported/no-validated-path`.
17
+ `npx --yes copilotkit@4.9.4 onboard read unsupported/no-validated-path`.
18
18
 
19
19
  ## Baseline proof subagent brief
20
20
 
@@ -40,7 +40,7 @@ Prove the live runtime in this order:
40
40
  4. Confirm from project files that the runtime constructor passes a `runner` option rather
41
41
  than an `intelligence` option. A package, import, project file, or key is not use proof.
42
42
  5. Run
43
- `npx --yes copilotkit@4.9.1 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
43
+ `npx --yes copilotkit@4.9.4 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
44
44
  with the runtime URL or auth header options that this project needs. Require exit zero
45
45
  and the JSON `ok` field to be `true`.
46
46
  6. Drive one real request through the existing frontend, CopilotKit runtime, and expected