copilotkit 4.26.0 → 4.27.0

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 (92) hide show
  1. package/README.md +271 -25
  2. package/cli-build-info.json +7 -7
  3. package/index.js +6785 -3294
  4. package/onboarding/index.json +2 -2
  5. package/onboarding/prompts/authenticate/start.md +28 -23
  6. package/onboarding/prompts/conversion/plan.md +3 -3
  7. package/onboarding/prompts/credentials/finalize-plan.md +34 -25
  8. package/onboarding/prompts/credentials/plan.md +46 -33
  9. package/onboarding/prompts/credentials/settle-credentials.md +38 -14
  10. package/onboarding/prompts/credentials/write-plan.md +104 -47
  11. package/onboarding/prompts/deployment/choose-local.md +17 -20
  12. package/onboarding/prompts/deployment/local-evaluation.md +45 -21
  13. package/onboarding/prompts/fallback/best-effort.md +11 -9
  14. package/onboarding/prompts/feature/a2ui/implement.md +4 -4
  15. package/onboarding/prompts/feature/a2ui/plan.md +3 -3
  16. package/onboarding/prompts/feature/a2ui/proof.md +5 -5
  17. package/onboarding/prompts/feature/a2ui/start.md +10 -8
  18. package/onboarding/prompts/feature/channels/implement.md +11 -8
  19. package/onboarding/prompts/feature/channels/plan.md +15 -7
  20. package/onboarding/prompts/feature/channels/proof.md +5 -5
  21. package/onboarding/prompts/feature/channels/start.md +11 -10
  22. package/onboarding/prompts/feature/chat-suggestions/implement.md +4 -4
  23. package/onboarding/prompts/feature/chat-suggestions/plan.md +3 -3
  24. package/onboarding/prompts/feature/chat-suggestions/proof.md +5 -5
  25. package/onboarding/prompts/feature/chat-suggestions/start.md +10 -8
  26. package/onboarding/prompts/feature/complete.md +2 -2
  27. package/onboarding/prompts/feature/learning/implement.md +14 -12
  28. package/onboarding/prompts/feature/learning/plan.md +4 -4
  29. package/onboarding/prompts/feature/learning/proof.md +24 -14
  30. package/onboarding/prompts/feature/learning/start.md +8 -8
  31. package/onboarding/prompts/feature/open-generative-ui/implement.md +4 -4
  32. package/onboarding/prompts/feature/open-generative-ui/plan.md +3 -3
  33. package/onboarding/prompts/feature/open-generative-ui/proof.md +5 -5
  34. package/onboarding/prompts/feature/open-generative-ui/start.md +10 -8
  35. package/onboarding/prompts/feature/realtime-sync/implement.md +7 -5
  36. package/onboarding/prompts/feature/realtime-sync/plan.md +3 -3
  37. package/onboarding/prompts/feature/realtime-sync/proof.md +5 -5
  38. package/onboarding/prompts/feature/realtime-sync/start.md +7 -7
  39. package/onboarding/prompts/feature/rich-threads/implement.md +8 -6
  40. package/onboarding/prompts/feature/rich-threads/plan.md +3 -3
  41. package/onboarding/prompts/feature/rich-threads/proof.md +5 -5
  42. package/onboarding/prompts/feature/rich-threads/start.md +7 -7
  43. package/onboarding/prompts/feature/stop.md +4 -4
  44. package/onboarding/prompts/feature/voice/implement.md +4 -4
  45. package/onboarding/prompts/feature/voice/plan.md +4 -4
  46. package/onboarding/prompts/feature/voice/proof.md +5 -5
  47. package/onboarding/prompts/feature/voice/start.md +10 -8
  48. package/onboarding/prompts/framework/ag2.md +20 -5
  49. package/onboarding/prompts/framework/agno.md +25 -9
  50. package/onboarding/prompts/framework/built-in.md +21 -6
  51. package/onboarding/prompts/framework/claude-sdk-python.md +11 -5
  52. package/onboarding/prompts/framework/claude-sdk-typescript.md +13 -6
  53. package/onboarding/prompts/framework/crewai-flows.md +24 -10
  54. package/onboarding/prompts/framework/custom-ag-ui.md +62 -28
  55. package/onboarding/prompts/framework/deep-agents.md +26 -9
  56. package/onboarding/prompts/framework/google-adk.md +18 -5
  57. package/onboarding/prompts/framework/langgraph-fastapi.md +20 -5
  58. package/onboarding/prompts/framework/langgraph-python.md +20 -5
  59. package/onboarding/prompts/framework/langgraph-typescript.md +27 -7
  60. package/onboarding/prompts/framework/llamaindex.md +24 -8
  61. package/onboarding/prompts/framework/mastra.md +21 -8
  62. package/onboarding/prompts/framework/ms-agent-dotnet.md +24 -6
  63. package/onboarding/prompts/framework/ms-agent-harness-dotnet.md +24 -5
  64. package/onboarding/prompts/framework/ms-agent-python.md +21 -5
  65. package/onboarding/prompts/framework/pydantic-ai.md +20 -5
  66. package/onboarding/prompts/framework/strands-python.md +27 -12
  67. package/onboarding/prompts/framework/strands-typescript.md +27 -12
  68. package/onboarding/prompts/frontend/angular.md +4 -4
  69. package/onboarding/prompts/frontend/nextjs.md +4 -4
  70. package/onboarding/prompts/frontend/plan.md +21 -13
  71. package/onboarding/prompts/frontend/react-native.md +3 -3
  72. package/onboarding/prompts/frontend/react-spa.md +3 -3
  73. package/onboarding/prompts/frontend/vue.md +3 -3
  74. package/onboarding/prompts/implementation/build-and-validate.md +25 -20
  75. package/onboarding/prompts/proof/complete.md +10 -7
  76. package/onboarding/prompts/proof/oss-baseline.md +6 -6
  77. package/onboarding/prompts/proof/round-trip.md +10 -10
  78. package/onboarding/prompts/research/gather.md +8 -8
  79. package/onboarding/prompts/research/merge.md +3 -3
  80. package/onboarding/prompts/research/preflight.md +2 -2
  81. package/onboarding/prompts/research/route.md +4 -4
  82. package/onboarding/prompts/setup/questions.md +192 -159
  83. package/onboarding/prompts/starter/clone.md +126 -51
  84. package/onboarding/prompts/stopped/run-failed.md +5 -3
  85. package/onboarding/prompts/subagent/create-plan.md +73 -20
  86. package/onboarding/prompts/subagent/implement-and-validate.md +30 -14
  87. package/onboarding/prompts/subagent/inspect-repository.md +3 -2
  88. package/onboarding/prompts/subagent/prove-oss-baseline.md +10 -5
  89. package/onboarding/prompts/subagent/prove-round-trip.md +23 -14
  90. package/onboarding/prompts/unsupported/no-validated-path.md +5 -4
  91. package/package.json +1 -1
  92. package/release/release-tool.js +12 -2
@@ -12,21 +12,25 @@ A local stack runs Learning only with a model that the developer gave it. Before
12
12
  run this command from the app directory:
13
13
 
14
14
  ```text
15
- npx --prefer-offline --yes copilotkit@4.26.0 local status --json
15
+ npx --prefer-offline --yes copilotkit@4.27.0 local status --json
16
16
  ```
17
17
 
18
18
  Read `learning.configuration`. If it is `configured`, continue with the proof. Any other
19
19
  value means that the stack has no Learning model.
20
20
 
21
- If the developer chose "configure later" in `deployment/choose-local`, and the run's plan
22
- records that choice, do not ask again. Continue with the proof, and report it as below.
21
+ Run `npx --prefer-offline --yes copilotkit@4.27.0 onboard setup-answers`. It holds the setup message's
22
+ answers, even after this conversation lost them. Take the Learning answer from the record,
23
+ or this conversation. If it is `later`, the developer chose "configure later" for the
24
+ Learning model on the local route, so do not ask again. The same holds when neither holds a
25
+ Learning answer: the run never asked and took that default. Continue with the proof, and report
26
+ it as below.
23
27
 
24
28
  Otherwise, tell the developer that Learning cannot process this container's threads until
25
29
  it has a model. Ask them to run this command in their own terminal window, in the app
26
30
  directory:
27
31
 
28
32
  ```text
29
- npx --prefer-offline --yes copilotkit@4.26.0 local setup
33
+ npx --prefer-offline --yes copilotkit@4.27.0 local setup
30
34
  ```
31
35
 
32
36
  Do not give it as a `!` line, and do not run it yourself. Its guided model prompt needs a
@@ -36,13 +40,13 @@ On a running stack, it restarts only Learning. The container and its threads sta
36
40
  ask the developer to write a model file, and do not read or print the model key.
37
41
 
38
42
  Say that the run continues when they reply or resume this session. Report the pause with
39
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-model-credential`, end your
43
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-model-credential`, end your
40
44
  turn, and wait. When the developer replies, run `local status --json` again.
41
45
  When it reports `configured`, continue with the proof.
42
46
 
43
47
  If the developer declines, continue with the proof, because the container assignment can
44
48
  still be proved. In the closing report, write "Learning configuration incomplete". Name the
45
- command that adds the model later: `npx --prefer-offline --yes copilotkit@4.26.0 local setup`, run from
49
+ command that adds the model later: `npx --prefer-offline --yes copilotkit@4.27.0 local setup`, run from
46
50
  the app directory. `learning.verified` is always `false`. It does not mean that Learning
47
51
  failed.
48
52
 
@@ -51,12 +55,18 @@ failed.
51
55
  One command decides it:
52
56
 
53
57
  ```text
54
- npx --prefer-offline --yes copilotkit@4.26.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --expect-learning-container <id> --json
58
+ npx --prefer-offline --yes copilotkit@4.27.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --expect-learning-container <id> --json
55
59
  ```
56
60
 
57
61
  It reads the thread back from the platform, so it answers for any runtime mount, and it
58
62
  passes only when that thread carries the container this run selected.
59
63
 
64
+ `verify` probes the runtime URL in `runtimeUrl` in `.copilotkit/project.json`, then in
65
+ `COPILOTKIT_RUNTIME_URL`, then on the port in the app's dev configuration. With none of
66
+ them, it assumes `http://localhost:3000/api/copilotkit`. If the dev server serves the
67
+ runtime anywhere else, add `--runtime-url <url>` with the real URL to each `verify`
68
+ command in this section.
69
+
60
70
  That command starts its own run on a new thread. An app that runs only threads it created,
61
71
  or whose `identifyUser` reads a session, refuses that run, and the container check never
62
72
  runs. Do not change the app to accept it. Send one request on a new thread in the app, as
@@ -64,11 +74,11 @@ a signed-in user, read that request's `threadId` from the request body the page
64
74
  the runtime, and prove the same thread. Where the page needs a sign-in, do not create an
65
75
  account and do not enter credentials. Where you cannot send the request yourself, ask the
66
76
  developer to send one message on a new thread and give you its thread id. Report the pause
67
- with `npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer`, then
77
+ with `npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer`, then
68
78
  end your turn and wait. When the developer gives the id, prove that thread:
69
79
 
70
80
  ```text
71
- npx --prefer-offline --yes copilotkit@4.26.0 verify --expect-runtime intelligence --thread <thread-id> --expect-learning-container <id> --json
81
+ npx --prefer-offline --yes copilotkit@4.27.0 verify --expect-runtime intelligence --thread <thread-id> --expect-learning-container <id> --json
72
82
  ```
73
83
 
74
84
  It reads that thread from the platform with the project key and starts no run.
@@ -98,7 +108,7 @@ That result is a question for the developer. Name the file and why the fix needs
98
108
  Before you end your turn to wait for the developer, report the pause:
99
109
 
100
110
  ```text
101
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
111
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
102
112
  ```
103
113
 
104
114
  Then end your turn and wait for the developer's answer. If they allow it, spawn a fresh
@@ -108,13 +118,13 @@ or the developer declines, take the feature stop route below.
108
118
  If the CLI prints `## Stop: this run deleted or moved the developer's work` instead of
109
119
  a step, show the developer the list it printed, and run what they choose:
110
120
  the `onboard restore` command the tripwire stop prints, which names each deleted file, or
111
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard tripwire --continue`. Then read the step again.
121
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard tripwire --continue`. Then read the step again.
112
122
 
113
123
  Report the outcome of each attempt as it ends, before any repair. The command counts the
114
124
  attempts and the repairs:
115
125
 
116
126
  ```text
117
- npx --prefer-offline --yes copilotkit@4.26.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
127
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
118
128
  ```
119
129
 
120
130
  Use `passed` only for a proved Container assignment, `failed` for an attempted proof that
@@ -123,9 +133,9 @@ failed, and `skipped` when the proof could not run.
123
133
  To route out and stop:
124
134
 
125
135
  ```text
126
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
136
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
127
137
  ```
128
138
 
129
139
  When the proof is recorded, run
130
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/complete` with the actual surface
140
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/complete` with the actual surface
131
141
  outcome.
@@ -9,7 +9,7 @@ subagents. Work only inside the target project and preserve its existing agent a
9
9
  Run this before anything else in this prompt:
10
10
 
11
11
  ```text
12
- npx --prefer-offline --yes copilotkit@4.26.0 onboard identify --coding-agent <coding-agent-slug> --model <model-id> --model-family <model-family>
12
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard identify --coding-agent <coding-agent-slug> --model <model-id> --model-family <model-family>
13
13
  ```
14
14
 
15
15
  Report your product slug, such as `codex` or `claude-code`. The command needs no sign-in,
@@ -38,13 +38,13 @@ carry on. Keep a read-only assignment read-only. If no subagent works at all, re
38
38
  once:
39
39
 
40
40
  ```text
41
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase delegation-unavailable
41
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase delegation-unavailable
42
42
  ```
43
43
 
44
44
  Before you end your turn to wait for the developer, report the pause:
45
45
 
46
46
  ```text
47
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
47
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
48
48
  ```
49
49
 
50
50
  A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
@@ -54,7 +54,7 @@ If you stop this run, send one short report before you stop. The friction comman
54
54
  the telemetry setting the developer already chose, so it needs no separate question.
55
55
 
56
56
  ```text
57
- npx --prefer-offline --yes copilotkit@4.26.0 onboard friction --phase stop --category <slug> --message "<sentences>"
57
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard friction --phase stop --category <slug> --message "<sentences>"
58
58
  ```
59
59
 
60
60
  `--message` takes one or two sentences: the step you stopped at and what stopped it.
@@ -84,7 +84,7 @@ status:
84
84
  before the capture, the inspection, and any edit:
85
85
 
86
86
  ```text
87
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/blocked-by-plan
87
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/blocked-by-plan
88
88
  ```
89
89
 
90
90
  - `LEARNING_AVAILABILITY_UNAVAILABLE` means the platform did not resolve the answer. It is
@@ -112,20 +112,20 @@ test/dev commands. Prove the current round trip and inspect `/info`.
112
112
  Wait for the inspection subagent to finish. Then report that the inspection came back:
113
113
 
114
114
  ```text
115
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase research-returned
115
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase research-returned
116
116
  ```
117
117
 
118
118
  If the inspection did not prove the baseline this intent extends, stop here without
119
119
  changing files:
120
120
 
121
121
  ```text
122
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
122
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
123
123
  ```
124
124
 
125
125
  When the inspection proved what this intent needs, read the next prompt now, in this turn:
126
126
 
127
127
  ```text
128
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/learning/plan
128
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/learning/plan
129
129
  ```
130
130
 
131
131
  That prompt holds the plan, the developer's approval, and the paths the plan changes.
@@ -22,7 +22,7 @@ That result is a question for the developer. Name the file and why the work need
22
22
  Before you end your turn to wait for the developer, report the pause:
23
23
 
24
24
  ```text
25
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
25
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
26
26
  ```
27
27
 
28
28
  Then end your turn and wait for the developer's answer. If they allow it, spawn a fresh
@@ -32,16 +32,16 @@ cannot ask, or the developer declines, take the feature stop route below.
32
32
  If the CLI prints `## Stop: this run deleted or moved the developer's work` instead of
33
33
  a step, show the developer the list it printed, and run what they choose:
34
34
  the `onboard restore` command the tripwire stop prints, which names each deleted file, or
35
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard tripwire --continue`. Then read the step again.
35
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard tripwire --continue`. Then read the step again.
36
36
 
37
37
  To route out and stop:
38
38
 
39
39
  ```text
40
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
40
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
41
41
  ```
42
42
 
43
43
  If validation cannot pass, or this intent needs a prerequisite the app does not have, use
44
44
  the feature stop route above without further changes.
45
45
 
46
46
  Otherwise run
47
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/open-generative-ui/proof`.
47
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/open-generative-ui/proof`.
@@ -12,7 +12,7 @@ The approval is a wait for the developer. Before you end your turn to wait, repo
12
12
  pause:
13
13
 
14
14
  ```text
15
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
15
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
16
16
  ```
17
17
 
18
18
  A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
@@ -47,7 +47,7 @@ likely CSP/sandbox implications, tests, and a user-visible generated UI proof. A
47
47
  Before you end your turn to wait for the developer, report the pause:
48
48
 
49
49
  ```text
50
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-plan-approval
50
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-plan-approval
51
51
  ```
52
52
 
53
53
  Ask the developer before you edit a file that has uncommitted changes. List those files in
@@ -55,4 +55,4 @@ the plan under `Uncommitted files`, each with one sentence explaining why, or wr
55
55
  `git status` names them. The CLI records no consent: the approved plan is the record. The
56
56
  plan must not delete, move, or rename one of those files.
57
57
 
58
- Then run `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/open-generative-ui/implement`.
58
+ Then run `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/open-generative-ui/implement`.
@@ -19,7 +19,7 @@ That result is a question for the developer. Name the file and why the fix needs
19
19
  Before you end your turn to wait for the developer, report the pause:
20
20
 
21
21
  ```text
22
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
22
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
23
23
  ```
24
24
 
25
25
  Then end your turn and wait for the developer's answer. If they allow it, spawn a fresh
@@ -29,13 +29,13 @@ or the developer declines, take the feature stop route below.
29
29
  If the CLI prints `## Stop: this run deleted or moved the developer's work` instead of
30
30
  a step, show the developer the list it printed, and run what they choose:
31
31
  the `onboard restore` command the tripwire stop prints, which names each deleted file, or
32
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard tripwire --continue`. Then read the step again.
32
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard tripwire --continue`. Then read the step again.
33
33
 
34
34
  Report the outcome of each attempt as it ends, before any repair. The command counts the
35
35
  attempts and the repairs:
36
36
 
37
37
  ```text
38
- npx --prefer-offline --yes copilotkit@4.26.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
38
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
39
39
  ```
40
40
 
41
41
  Use `passed` only for a proved generated UI, `failed` for an attempted proof that failed,
@@ -44,9 +44,9 @@ and `skipped` when the proof could not run.
44
44
  To route out and stop:
45
45
 
46
46
  ```text
47
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
47
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
48
48
  ```
49
49
 
50
50
  When the proof is recorded, run
51
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/complete` with the outcome actually
51
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/complete` with the outcome actually
52
52
  observed.
@@ -8,7 +8,7 @@ implementation, and proof subagents, all restricted to the target project direct
8
8
  Run this before anything else in this prompt:
9
9
 
10
10
  ```text
11
- npx --prefer-offline --yes copilotkit@4.26.0 onboard identify --coding-agent <coding-agent-slug> --model <model-id> --model-family <model-family>
11
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard identify --coding-agent <coding-agent-slug> --model <model-id> --model-family <model-family>
12
12
  ```
13
13
 
14
14
  Report your product slug, such as `codex` or `claude-code`. The command needs no sign-in,
@@ -37,13 +37,13 @@ carry on. Keep a read-only assignment read-only. If no subagent works at all, re
37
37
  once:
38
38
 
39
39
  ```text
40
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase delegation-unavailable
40
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase delegation-unavailable
41
41
  ```
42
42
 
43
43
  Before you end your turn to wait for the developer, report the pause:
44
44
 
45
45
  ```text
46
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
46
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
47
47
  ```
48
48
 
49
49
  A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
@@ -53,7 +53,7 @@ If you stop this run, send one short report before you stop. The friction comman
53
53
  the telemetry setting the developer already chose, so it needs no separate question.
54
54
 
55
55
  ```text
56
- npx --prefer-offline --yes copilotkit@4.26.0 onboard friction --phase stop --category <slug> --message "<sentences>"
56
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard friction --phase stop --category <slug> --message "<sentences>"
57
57
  ```
58
58
 
59
59
  `--message` takes one or two sentences: the step you stopped at and what stopped it.
@@ -70,26 +70,28 @@ before a subagent or a project process runs.
70
70
  Before edits, have a research subagent identify the current CopilotKit runtime route,
71
71
  provider/chat component, agent id, package versions, existing middleware, sandbox/CSP
72
72
  constraints, and normal test/dev commands. Prove the existing app first with `/info`,
73
- `npx --prefer-offline --yes copilotkit@4.26.0 verify --expect-runtime oss --round-trip --agent <agent-id> --json`,
73
+ `npx --prefer-offline --yes copilotkit@4.27.0 verify --expect-runtime oss --round-trip --agent <agent-id> --json`,
74
74
  and a real frontend request when browser control is available.
75
+ The `verify` report names the runtime URL it probed. If the dev server serves the
76
+ runtime at another URL, add `--runtime-url <url>`.
75
77
 
76
78
  Wait for the inspection subagent to finish. Then report that the inspection came back:
77
79
 
78
80
  ```text
79
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase research-returned
81
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase research-returned
80
82
  ```
81
83
 
82
84
  If the inspection did not prove the baseline this intent extends, stop here without
83
85
  changing files:
84
86
 
85
87
  ```text
86
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
88
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
87
89
  ```
88
90
 
89
91
  When the inspection proved what this intent needs, read the next prompt now, in this turn:
90
92
 
91
93
  ```text
92
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/open-generative-ui/plan
94
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/open-generative-ui/plan
93
95
  ```
94
96
 
95
97
  That prompt holds the plan, the developer's approval, and the paths the plan changes.
@@ -18,7 +18,9 @@ such an app on a thread the app created, with `--thread <id>`, which needs no se
18
18
  record UNKNOWN as the expected result here.
19
19
 
20
20
  Run focused tests and
21
- `npx --prefer-offline --yes copilotkit@4.26.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
21
+ `npx --prefer-offline --yes copilotkit@4.27.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
22
+ The `verify` report names the runtime URL it probed. If the dev server serves the
23
+ runtime at another URL, add `--runtime-url <url>`.
22
24
  Repair changed-file failures and record changed paths and secret-safe validation
23
25
  evidence.
24
26
 
@@ -31,7 +33,7 @@ That result is a question for the developer. Name the file and why the work need
31
33
  Before you end your turn to wait for the developer, report the pause:
32
34
 
33
35
  ```text
34
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
36
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
35
37
  ```
36
38
 
37
39
  Then end your turn and wait for the developer's answer. If they allow it, spawn a fresh
@@ -41,16 +43,16 @@ cannot ask, or the developer declines, take the feature stop route below.
41
43
  If the CLI prints `## Stop: this run deleted or moved the developer's work` instead of
42
44
  a step, show the developer the list it printed, and run what they choose:
43
45
  the `onboard restore` command the tripwire stop prints, which names each deleted file, or
44
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard tripwire --continue`. Then read the step again.
46
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard tripwire --continue`. Then read the step again.
45
47
 
46
48
  To route out and stop:
47
49
 
48
50
  ```text
49
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
51
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
50
52
  ```
51
53
 
52
54
  If validation cannot pass, or this intent needs a prerequisite the app does not have, use
53
55
  the feature stop route above without further changes.
54
56
 
55
57
  Otherwise run
56
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/realtime-sync/proof`.
58
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/realtime-sync/proof`.
@@ -12,7 +12,7 @@ The approval is a wait for the developer. Before you end your turn to wait, repo
12
12
  pause:
13
13
 
14
14
  ```text
15
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
15
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
16
16
  ```
17
17
 
18
18
  A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
@@ -52,7 +52,7 @@ need a `wsUrl`. Ask for approval as its own question.
52
52
  Before you end your turn to wait for the developer, report the pause:
53
53
 
54
54
  ```text
55
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-plan-approval
55
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-plan-approval
56
56
  ```
57
57
 
58
58
  Ask the developer before you edit a file that has uncommitted changes. List those files in
@@ -60,4 +60,4 @@ the plan under `Uncommitted files`, each with one sentence explaining why, or wr
60
60
  `git status` names them. The CLI records no consent: the approved plan is the record. The
61
61
  plan must not delete, move, or rename one of those files.
62
62
 
63
- Then run `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/realtime-sync/implement`.
63
+ Then run `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/realtime-sync/implement`.
@@ -21,7 +21,7 @@ That result is a question for the developer. Name the file and why the fix needs
21
21
  Before you end your turn to wait for the developer, report the pause:
22
22
 
23
23
  ```text
24
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
24
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
25
25
  ```
26
26
 
27
27
  Then end your turn and wait for the developer's answer. If they allow it, spawn a fresh
@@ -31,13 +31,13 @@ or the developer declines, take the feature stop route below.
31
31
  If the CLI prints `## Stop: this run deleted or moved the developer's work` instead of
32
32
  a step, show the developer the list it printed, and run what they choose:
33
33
  the `onboard restore` command the tripwire stop prints, which names each deleted file, or
34
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard tripwire --continue`. Then read the step again.
34
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard tripwire --continue`. Then read the step again.
35
35
 
36
36
  Report the outcome of each attempt as it ends, before any repair. The command counts the
37
37
  attempts and the repairs:
38
38
 
39
39
  ```text
40
- npx --prefer-offline --yes copilotkit@4.26.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
40
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
41
41
  ```
42
42
 
43
43
  Use `passed` only for proved two-client sync, `failed` for an attempted proof that failed,
@@ -46,8 +46,8 @@ and `skipped` when the proof could not run.
46
46
  To route out and stop:
47
47
 
48
48
  ```text
49
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
49
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
50
50
  ```
51
51
 
52
52
  When the proof is recorded, run
53
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/complete` with the actual outcome.
53
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/complete` with the actual outcome.
@@ -9,7 +9,7 @@ two-context proof to subagents within the target project.
9
9
  Run this before anything else in this prompt:
10
10
 
11
11
  ```text
12
- npx --prefer-offline --yes copilotkit@4.26.0 onboard identify --coding-agent <coding-agent-slug> --model <model-id> --model-family <model-family>
12
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard identify --coding-agent <coding-agent-slug> --model <model-id> --model-family <model-family>
13
13
  ```
14
14
 
15
15
  Report your product slug, such as `codex` or `claude-code`. The command needs no sign-in,
@@ -38,13 +38,13 @@ carry on. Keep a read-only assignment read-only. If no subagent works at all, re
38
38
  once:
39
39
 
40
40
  ```text
41
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase delegation-unavailable
41
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase delegation-unavailable
42
42
  ```
43
43
 
44
44
  Before you end your turn to wait for the developer, report the pause:
45
45
 
46
46
  ```text
47
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
47
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
48
48
  ```
49
49
 
50
50
  A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
@@ -54,7 +54,7 @@ If you stop this run, send one short report before you stop. The friction comman
54
54
  the telemetry setting the developer already chose, so it needs no separate question.
55
55
 
56
56
  ```text
57
- npx --prefer-offline --yes copilotkit@4.26.0 onboard friction --phase stop --category <slug> --message "<sentences>"
57
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard friction --phase stop --category <slug> --message "<sentences>"
58
58
  ```
59
59
 
60
60
  `--message` takes one or two sentences: the step you stopped at and what stopped it.
@@ -76,20 +76,20 @@ round trip and inspect `/info`.
76
76
  Wait for the inspection subagent to finish. Then report that the inspection came back:
77
77
 
78
78
  ```text
79
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase research-returned
79
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase research-returned
80
80
  ```
81
81
 
82
82
  If the inspection did not prove the baseline this intent extends, stop here without
83
83
  changing files:
84
84
 
85
85
  ```text
86
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
86
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
87
87
  ```
88
88
 
89
89
  When the inspection proved what this intent needs, read the next prompt now, in this turn:
90
90
 
91
91
  ```text
92
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/realtime-sync/plan
92
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/realtime-sync/plan
93
93
  ```
94
94
 
95
95
  That prompt holds the plan, the developer's approval, and the paths the plan changes.
@@ -2,7 +2,7 @@
2
2
 
3
3
  Delegate implementation to one subagent with the approved plan and fetched official guides.
4
4
  If repository evidence does not prove an existing valid Intelligence selection, run
5
- `npx --prefer-offline --yes copilotkit@4.26.0 login --json` and follow its single streaming session. Then
5
+ `npx --prefer-offline --yes copilotkit@4.27.0 login --json` and follow its single streaming session. Then
6
6
  list projects, show the developer the current/recent choices, and select or create one only
7
7
  after they choose. Require the secret-safe selection summary to confirm the project file,
8
8
  environment file, and key provisioning; never display a key. If existing configuration is
@@ -21,7 +21,9 @@ such an app on a thread the app created, with `--thread <id>`, which needs no se
21
21
  record UNKNOWN as the expected result here.
22
22
 
23
23
  Run focused type/test commands, then start the app and run
24
- `npx --prefer-offline --yes copilotkit@4.26.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
24
+ `npx --prefer-offline --yes copilotkit@4.27.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
25
+ The `verify` report names the runtime URL it probed. If the dev server serves the
26
+ runtime at another URL, add `--runtime-url <url>`.
25
27
  Repair changed-file failures before continuing. Record changed paths and secret-safe
26
28
  validation evidence.
27
29
 
@@ -34,7 +36,7 @@ That result is a question for the developer. Name the file and why the work need
34
36
  Before you end your turn to wait for the developer, report the pause:
35
37
 
36
38
  ```text
37
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
39
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
38
40
  ```
39
41
 
40
42
  Then end your turn and wait for the developer's answer. If they allow it, spawn a fresh
@@ -44,16 +46,16 @@ cannot ask, or the developer declines, take the feature stop route below.
44
46
  If the CLI prints `## Stop: this run deleted or moved the developer's work` instead of
45
47
  a step, show the developer the list it printed, and run what they choose:
46
48
  the `onboard restore` command the tripwire stop prints, which names each deleted file, or
47
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard tripwire --continue`. Then read the step again.
49
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard tripwire --continue`. Then read the step again.
48
50
 
49
51
  To route out and stop:
50
52
 
51
53
  ```text
52
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
54
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
53
55
  ```
54
56
 
55
57
  If validation cannot pass, or this intent needs a prerequisite the app does not have, use
56
58
  the feature stop route above without further changes.
57
59
 
58
60
  Otherwise run
59
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/rich-threads/proof`.
61
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/rich-threads/proof`.
@@ -12,7 +12,7 @@ The approval is a wait for the developer. Before you end your turn to wait, repo
12
12
  pause:
13
13
 
14
14
  ```text
15
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
15
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
16
16
  ```
17
17
 
18
18
  A turn that ends while the run waits is a pause, not a stop, even when your harness ends it.
@@ -54,7 +54,7 @@ tests, and a reload/reopen proof. Ask for approval as its own question.
54
54
  Before you end your turn to wait for the developer, report the pause:
55
55
 
56
56
  ```text
57
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-plan-approval
57
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-plan-approval
58
58
  ```
59
59
 
60
60
  Ask the developer before you edit a file that has uncommitted changes. List those files in
@@ -62,4 +62,4 @@ the plan under `Uncommitted files`, each with one sentence explaining why, or wr
62
62
  `git status` names them. The CLI records no consent: the approved plan is the record. The
63
63
  plan must not delete, move, or rename one of those files.
64
64
 
65
- Then run `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/rich-threads/implement`.
65
+ Then run `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/rich-threads/implement`.
@@ -20,7 +20,7 @@ That result is a question for the developer. Name the file and why the fix needs
20
20
  Before you end your turn to wait for the developer, report the pause:
21
21
 
22
22
  ```text
23
- npx --prefer-offline --yes copilotkit@4.26.0 onboard checkpoint --phase awaiting-developer
23
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard checkpoint --phase awaiting-developer
24
24
  ```
25
25
 
26
26
  Then end your turn and wait for the developer's answer. If they allow it, spawn a fresh
@@ -30,13 +30,13 @@ or the developer declines, take the feature stop route below.
30
30
  If the CLI prints `## Stop: this run deleted or moved the developer's work` instead of
31
31
  a step, show the developer the list it printed, and run what they choose:
32
32
  the `onboard restore` command the tripwire stop prints, which names each deleted file, or
33
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard tripwire --continue`. Then read the step again.
33
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard tripwire --continue`. Then read the step again.
34
34
 
35
35
  Report the outcome of each attempt as it ends, before any repair. The command counts the
36
36
  attempts and the repairs:
37
37
 
38
38
  ```text
39
- npx --prefer-offline --yes copilotkit@4.26.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
39
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
40
40
  ```
41
41
 
42
42
  Use `passed` only for proved persistence and reopen, `failed` for an attempted proof that
@@ -45,9 +45,9 @@ failed, and `skipped` when the proof could not run.
45
45
  To route out and stop:
46
46
 
47
47
  ```text
48
- npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/stop
48
+ npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/stop
49
49
  ```
50
50
 
51
51
  When the proof is recorded, run
52
- `npx --prefer-offline --yes copilotkit@4.26.0 onboard read feature/complete` with the actual browser
52
+ `npx --prefer-offline --yes copilotkit@4.27.0 onboard read feature/complete` with the actual browser
53
53
  outcome.