copilotkit 4.12.0 → 4.13.1

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 (80) hide show
  1. package/README.md +10 -0
  2. package/cli-build-info.json +7 -7
  3. package/index.js +1590 -348
  4. package/onboarding/index.json +20 -2
  5. package/onboarding/prompts/authenticate/start.md +38 -33
  6. package/onboarding/prompts/conversion/plan.md +3 -3
  7. package/onboarding/prompts/credentials/finalize-plan.md +9 -8
  8. package/onboarding/prompts/credentials/plan.md +26 -20
  9. package/onboarding/prompts/credentials/settle-credentials.md +8 -8
  10. package/onboarding/prompts/credentials/write-plan.md +19 -6
  11. package/onboarding/prompts/fallback/best-effort.md +6 -6
  12. package/onboarding/prompts/feature/a2ui/implement.md +6 -6
  13. package/onboarding/prompts/feature/a2ui/proof.md +6 -6
  14. package/onboarding/prompts/feature/a2ui/start.md +7 -7
  15. package/onboarding/prompts/feature/channels/implement.md +75 -12
  16. package/onboarding/prompts/feature/channels/proof.md +13 -6
  17. package/onboarding/prompts/feature/channels/start.md +27 -10
  18. package/onboarding/prompts/feature/chat-suggestions/implement.md +6 -6
  19. package/onboarding/prompts/feature/chat-suggestions/proof.md +6 -6
  20. package/onboarding/prompts/feature/chat-suggestions/start.md +7 -7
  21. package/onboarding/prompts/feature/complete.md +1 -1
  22. package/onboarding/prompts/feature/learning/implement.md +15 -15
  23. package/onboarding/prompts/feature/learning/proof.md +7 -7
  24. package/onboarding/prompts/feature/learning/start.md +8 -8
  25. package/onboarding/prompts/feature/open-generative-ui/implement.md +6 -6
  26. package/onboarding/prompts/feature/open-generative-ui/proof.md +6 -6
  27. package/onboarding/prompts/feature/open-generative-ui/start.md +7 -7
  28. package/onboarding/prompts/feature/realtime-sync/implement.md +7 -7
  29. package/onboarding/prompts/feature/realtime-sync/proof.md +6 -6
  30. package/onboarding/prompts/feature/realtime-sync/start.md +6 -6
  31. package/onboarding/prompts/feature/rich-threads/implement.md +8 -8
  32. package/onboarding/prompts/feature/rich-threads/proof.md +6 -6
  33. package/onboarding/prompts/feature/rich-threads/start.md +6 -6
  34. package/onboarding/prompts/feature/stop.md +2 -2
  35. package/onboarding/prompts/feature/voice/implement.md +6 -6
  36. package/onboarding/prompts/feature/voice/proof.md +6 -6
  37. package/onboarding/prompts/feature/voice/start.md +7 -7
  38. package/onboarding/prompts/framework/ag2.md +2 -2
  39. package/onboarding/prompts/framework/agno.md +2 -2
  40. package/onboarding/prompts/framework/built-in.md +4 -2
  41. package/onboarding/prompts/framework/claude-sdk-python.md +2 -2
  42. package/onboarding/prompts/framework/claude-sdk-typescript.md +2 -2
  43. package/onboarding/prompts/framework/crewai-flows.md +2 -2
  44. package/onboarding/prompts/framework/deep-agents.md +5 -2
  45. package/onboarding/prompts/framework/google-adk.md +4 -2
  46. package/onboarding/prompts/framework/langgraph-fastapi.md +4 -3
  47. package/onboarding/prompts/framework/langgraph-python.md +6 -2
  48. package/onboarding/prompts/framework/langgraph-typescript.md +6 -2
  49. package/onboarding/prompts/framework/llamaindex.md +2 -2
  50. package/onboarding/prompts/framework/mastra.md +4 -2
  51. package/onboarding/prompts/framework/ms-agent-dotnet.md +4 -2
  52. package/onboarding/prompts/framework/ms-agent-harness-dotnet.md +2 -2
  53. package/onboarding/prompts/framework/ms-agent-python.md +4 -2
  54. package/onboarding/prompts/framework/pydantic-ai.md +2 -2
  55. package/onboarding/prompts/framework/strands-python.md +4 -2
  56. package/onboarding/prompts/framework/strands-typescript.md +4 -2
  57. package/onboarding/prompts/frontend/angular.md +3 -3
  58. package/onboarding/prompts/frontend/nextjs.md +3 -3
  59. package/onboarding/prompts/frontend/plan.md +21 -10
  60. package/onboarding/prompts/frontend/react-native.md +2 -2
  61. package/onboarding/prompts/frontend/react-spa.md +2 -2
  62. package/onboarding/prompts/frontend/vue.md +2 -2
  63. package/onboarding/prompts/implementation/build-and-validate.md +33 -15
  64. package/onboarding/prompts/proof/complete.md +35 -16
  65. package/onboarding/prompts/proof/oss-baseline.md +5 -5
  66. package/onboarding/prompts/proof/round-trip.md +23 -12
  67. package/onboarding/prompts/research/gather.md +12 -102
  68. package/onboarding/prompts/research/merge.md +60 -0
  69. package/onboarding/prompts/research/preflight.md +75 -0
  70. package/onboarding/prompts/research/route.md +30 -6
  71. package/onboarding/prompts/starter/clone.md +5 -5
  72. package/onboarding/prompts/stopped/run-failed.md +2 -2
  73. package/onboarding/prompts/subagent/create-plan.md +18 -1
  74. package/onboarding/prompts/subagent/implement-and-validate.md +37 -0
  75. package/onboarding/prompts/subagent/inspect-repository.md +1 -1
  76. package/onboarding/prompts/subagent/prove-oss-baseline.md +1 -1
  77. package/onboarding/prompts/subagent/prove-round-trip.md +17 -7
  78. package/onboarding/prompts/unsupported/no-validated-path.md +2 -2
  79. package/package.json +4 -1
  80. package/release/release-tool.js +101 -1
@@ -7,7 +7,7 @@ Container. Confirm the thread remains associated with the expected user.
7
7
  One command decides it:
8
8
 
9
9
  ```text
10
- npx --yes copilotkit@4.12.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --expect-learning-container <id> --json
10
+ npx --yes copilotkit@4.13.1 verify --expect-runtime intelligence --round-trip --agent <agent-id> --expect-learning-container <id> --json
11
11
  ```
12
12
 
13
13
  It reads the thread back from the platform, so it answers for any runtime mount, and it
@@ -32,24 +32,24 @@ same threshold. Existing threads do not join automatically just because a contai
32
32
  Report each attempt at the proof as it ends, counting from one:
33
33
 
34
34
  ```text
35
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase journey-attempted --attempt 1
35
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase journey-attempted --attempt 1
36
36
  ```
37
37
 
38
38
  Report each repair cycle the same way, counting from one:
39
39
 
40
40
  ```text
41
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase repair-attempted --attempt 1
41
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase repair-attempted --attempt 1
42
42
  ```
43
43
 
44
44
  After the final attempt, report the gate exactly once:
45
45
 
46
46
  ```text
47
- npx --yes copilotkit@4.12.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
47
+ npx --yes copilotkit@4.13.1 onboard proof --step round-trip --outcome <passed|failed|skipped>
48
48
  ```
49
49
 
50
50
  Use `passed` only for a proved Container assignment, `failed` for an attempted proof that
51
51
  failed, and `skipped` when the proof could not run. Then run
52
- `npx --yes copilotkit@4.12.0 onboard audit`. Continue only when it starts with
52
+ `npx --yes copilotkit@4.13.1 onboard audit`. Continue only when it starts with
53
53
  `Status: passed`.
54
54
 
55
55
  If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -64,9 +64,9 @@ Run the audit again after each accepted or authorized change.
64
64
  If the audit still fails, or starts with `Status: blocked`, route out and stop:
65
65
 
66
66
  ```text
67
- npx --yes copilotkit@4.12.0 onboard read feature/stop
67
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
68
68
  ```
69
69
 
70
70
  When the audit passes, run
71
- `npx --yes copilotkit@4.12.0 onboard read feature/complete` with the actual surface
71
+ `npx --yes copilotkit@4.13.1 onboard read feature/complete` with the actual surface
72
72
  outcome.
@@ -11,7 +11,7 @@ friction command without another developer question. Do not ask the developer ab
11
11
  telemetry: the command applies the setting they already have.
12
12
 
13
13
  ```text
14
- npx --yes copilotkit@4.12.0 onboard friction --phase stop --category <slug>
14
+ npx --yes copilotkit@4.13.1 onboard friction --phase stop --category <slug>
15
15
  ```
16
16
 
17
17
  Write one or two sentences to standard input: the step you stopped at and what stopped it.
@@ -38,7 +38,7 @@ status:
38
38
  before the capture, the inspection, and any edit:
39
39
 
40
40
  ```text
41
- npx --yes copilotkit@4.12.0 onboard read feature/blocked-by-plan
41
+ npx --yes copilotkit@4.13.1 onboard read feature/blocked-by-plan
42
42
  ```
43
43
 
44
44
  - `LEARNING_AVAILABILITY_UNAVAILABLE` means the platform did not resolve the answer. It is
@@ -59,7 +59,7 @@ again: it has no answer, so it carries the question forward rather than ending o
59
59
  Before any subagent or project process runs, capture the developer's existing work:
60
60
 
61
61
  ```text
62
- npx --yes copilotkit@4.12.0 onboard protect
62
+ npx --yes copilotkit@4.13.1 onboard protect
63
63
  ```
64
64
 
65
65
  Keep the exact protected path list it prints and give that list to every subagent. No
@@ -75,7 +75,7 @@ onboarding.
75
75
  Wait for the inspection subagent to finish. Then report that the inspection came back:
76
76
 
77
77
  ```text
78
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase research-returned
78
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase research-returned
79
79
  ```
80
80
 
81
81
  A refused checkpoint prints its reason and leaves onboarding unaffected. It is not a
@@ -85,7 +85,7 @@ If the inspection did not prove the baseline this intent extends, stop here with
85
85
  changing files:
86
86
 
87
87
  ```text
88
- npx --yes copilotkit@4.12.0 onboard read feature/stop
88
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
89
89
  ```
90
90
 
91
91
  Fetch the current official guides before planning:
@@ -117,7 +117,7 @@ one.
117
117
  After approval, record each approved path before implementation:
118
118
 
119
119
  ```text
120
- npx --yes copilotkit@4.12.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
120
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
121
121
  ```
122
122
 
123
123
  If an approved path changed after capture and no implementation step has run, add
@@ -127,7 +127,7 @@ authorize a path the approved plan did not list.
127
127
  Then report the plan this run is about to implement:
128
128
 
129
129
  ```text
130
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase plan-written
130
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase plan-written
131
131
  ```
132
132
 
133
- Then run `npx --yes copilotkit@4.12.0 onboard read feature/learning/implement`.
133
+ Then run `npx --yes copilotkit@4.13.1 onboard read feature/learning/implement`.
@@ -16,7 +16,7 @@ validation results without secrets.
16
16
  After validation and each repair, run:
17
17
 
18
18
  ```text
19
- npx --yes copilotkit@4.12.0 onboard audit
19
+ npx --yes copilotkit@4.13.1 onboard audit
20
20
  ```
21
21
 
22
22
  Continue only when it starts with `Status: passed`. A path under `Authorized to modify:` is
@@ -27,7 +27,7 @@ with the implementation subagent's `Files changed` section. If that section does
27
27
  the path, accept the developer's external change:
28
28
 
29
29
  ```text
30
- npx --yes copilotkit@4.12.0 onboard protect --accept-external --path <path>
30
+ npx --yes copilotkit@4.13.1 onboard protect --accept-external --path <path>
31
31
  ```
32
32
 
33
33
  For an env file where the developer placed a requested credential, use
@@ -36,24 +36,24 @@ or its report does not settle who changed it, ask the developer to allow the unp
36
36
  change. Only after they agree, record their answer:
37
37
 
38
38
  ```text
39
- npx --yes copilotkit@4.12.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
39
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
40
40
  ```
41
41
 
42
42
  Run the audit again after each accepted or authorized change. If it still fails, or starts
43
43
  with `Status: blocked`, route out and stop:
44
44
 
45
45
  ```text
46
- npx --yes copilotkit@4.12.0 onboard read feature/stop
46
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
47
47
  ```
48
48
 
49
49
  When implementation validation passes, report it:
50
50
 
51
51
  ```text
52
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase build-validated
52
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase build-validated
53
53
  ```
54
54
 
55
55
  If validation cannot pass, or this intent needs a prerequisite the app does not have, use
56
56
  the feature stop route above without further changes.
57
57
 
58
58
  Otherwise run
59
- `npx --yes copilotkit@4.12.0 onboard read feature/open-generative-ui/proof`.
59
+ `npx --yes copilotkit@4.13.1 onboard read feature/open-generative-ui/proof`.
@@ -13,23 +13,23 @@ the missing visual proof honestly.
13
13
  Report each attempt at the proof as it ends, counting from one:
14
14
 
15
15
  ```text
16
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase journey-attempted --attempt 1
16
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase journey-attempted --attempt 1
17
17
  ```
18
18
 
19
19
  Report each repair cycle the same way, counting from one:
20
20
 
21
21
  ```text
22
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase repair-attempted --attempt 1
22
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase repair-attempted --attempt 1
23
23
  ```
24
24
 
25
25
  After the final attempt, report the gate exactly once:
26
26
 
27
27
  ```text
28
- npx --yes copilotkit@4.12.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
28
+ npx --yes copilotkit@4.13.1 onboard proof --step round-trip --outcome <passed|failed|skipped>
29
29
  ```
30
30
 
31
31
  Use `passed` only for a proved generated UI, `failed` for an attempted proof that failed,
32
- and `skipped` when the proof could not run. Then run `npx --yes copilotkit@4.12.0 onboard audit`.
32
+ and `skipped` when the proof could not run. Then run `npx --yes copilotkit@4.13.1 onboard audit`.
33
33
  Continue only when it starts with `Status: passed`.
34
34
 
35
35
  If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -44,9 +44,9 @@ Run the audit again after each accepted or authorized change.
44
44
  If the audit still fails, or starts with `Status: blocked`, route out and stop:
45
45
 
46
46
  ```text
47
- npx --yes copilotkit@4.12.0 onboard read feature/stop
47
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
48
48
  ```
49
49
 
50
50
  When the audit passes, run
51
- `npx --yes copilotkit@4.12.0 onboard read feature/complete` with the outcome actually
51
+ `npx --yes copilotkit@4.13.1 onboard read feature/complete` with the outcome actually
52
52
  observed.
@@ -6,7 +6,7 @@ implementation, and proof subagents, all restricted to the target project direct
6
6
  Before any subagent or project process runs, capture the developer's existing work:
7
7
 
8
8
  ```text
9
- npx --yes copilotkit@4.12.0 onboard protect
9
+ npx --yes copilotkit@4.13.1 onboard protect
10
10
  ```
11
11
 
12
12
  Keep the exact protected path list it prints and give that list to every subagent. No
@@ -16,7 +16,7 @@ approved authorization before implementation.
16
16
  Before edits, have a research subagent identify the current CopilotKit runtime route,
17
17
  provider/chat component, agent id, package versions, existing middleware, sandbox/CSP
18
18
  constraints, and normal test/dev commands. Prove the existing app first with `/info`,
19
- `npx --yes copilotkit@4.12.0 verify --expect-runtime oss --round-trip --agent <agent-id> --json`,
19
+ `npx --yes copilotkit@4.13.1 verify --expect-runtime oss --round-trip --agent <agent-id> --json`,
20
20
  and a real frontend request when browser control is available. If the app is not an existing
21
21
  OSS CopilotKit app with a proven round trip, change nothing and direct the developer to the
22
22
  generic onboarding path first.
@@ -24,7 +24,7 @@ generic onboarding path first.
24
24
  Wait for the inspection subagent to finish. Then report that the inspection came back:
25
25
 
26
26
  ```text
27
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase research-returned
27
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase research-returned
28
28
  ```
29
29
 
30
30
  A refused checkpoint prints its reason and leaves onboarding unaffected. It is not a
@@ -34,7 +34,7 @@ If the inspection did not prove the baseline this intent extends, stop here with
34
34
  changing files:
35
35
 
36
36
  ```text
37
- npx --yes copilotkit@4.12.0 onboard read feature/stop
37
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
38
38
  ```
39
39
 
40
40
  Do not sign in, select an Intelligence project, create credentials, change the existing
@@ -56,7 +56,7 @@ one.
56
56
  After approval, record each approved path before implementation:
57
57
 
58
58
  ```text
59
- npx --yes copilotkit@4.12.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
59
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
60
60
  ```
61
61
 
62
62
  If an approved path changed after capture and no implementation step has run, add
@@ -66,7 +66,7 @@ authorize a path the approved plan did not list.
66
66
  Then report the plan this run is about to implement:
67
67
 
68
68
  ```text
69
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase plan-written
69
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase plan-written
70
70
  ```
71
71
 
72
- Then run `npx --yes copilotkit@4.12.0 onboard read feature/open-generative-ui/implement`.
72
+ Then run `npx --yes copilotkit@4.13.1 onboard read feature/open-generative-ui/implement`.
@@ -17,14 +17,14 @@ non-zero on an app that is working. Pass what `identifyUser` reads with a repeat
17
17
  It is not a defect to repair.
18
18
 
19
19
  Run focused tests and
20
- `npx --yes copilotkit@4.12.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
20
+ `npx --yes copilotkit@4.13.1 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
21
21
  Repair changed-file failures and record changed paths and secret-safe validation
22
22
  evidence.
23
23
 
24
24
  After validation and each repair, run:
25
25
 
26
26
  ```text
27
- npx --yes copilotkit@4.12.0 onboard audit
27
+ npx --yes copilotkit@4.13.1 onboard audit
28
28
  ```
29
29
 
30
30
  Continue only when it starts with `Status: passed`. A path under `Authorized to modify:` is
@@ -35,7 +35,7 @@ with the implementation subagent's `Files changed` section. If that section does
35
35
  the path, accept the developer's external change:
36
36
 
37
37
  ```text
38
- npx --yes copilotkit@4.12.0 onboard protect --accept-external --path <path>
38
+ npx --yes copilotkit@4.13.1 onboard protect --accept-external --path <path>
39
39
  ```
40
40
 
41
41
  For an env file where the developer placed a requested credential, use
@@ -44,24 +44,24 @@ or its report does not settle who changed it, ask the developer to allow the unp
44
44
  change. Only after they agree, record their answer:
45
45
 
46
46
  ```text
47
- npx --yes copilotkit@4.12.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
47
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
48
48
  ```
49
49
 
50
50
  Run the audit again after each accepted or authorized change. If it still fails, or starts
51
51
  with `Status: blocked`, route out and stop:
52
52
 
53
53
  ```text
54
- npx --yes copilotkit@4.12.0 onboard read feature/stop
54
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
55
55
  ```
56
56
 
57
57
  When implementation validation passes, report it:
58
58
 
59
59
  ```text
60
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase build-validated
60
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase build-validated
61
61
  ```
62
62
 
63
63
  If validation cannot pass, or this intent needs a prerequisite the app does not have, use
64
64
  the feature stop route above without further changes.
65
65
 
66
66
  Otherwise run
67
- `npx --yes copilotkit@4.12.0 onboard read feature/realtime-sync/proof`.
67
+ `npx --yes copilotkit@4.13.1 onboard read feature/realtime-sync/proof`.
@@ -14,23 +14,23 @@ the missing proof rather than claiming realtime works.
14
14
  Report each attempt at the proof as it ends, counting from one:
15
15
 
16
16
  ```text
17
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase journey-attempted --attempt 1
17
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase journey-attempted --attempt 1
18
18
  ```
19
19
 
20
20
  Report each repair cycle the same way, counting from one:
21
21
 
22
22
  ```text
23
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase repair-attempted --attempt 1
23
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase repair-attempted --attempt 1
24
24
  ```
25
25
 
26
26
  After the final attempt, report the gate exactly once:
27
27
 
28
28
  ```text
29
- npx --yes copilotkit@4.12.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
29
+ npx --yes copilotkit@4.13.1 onboard proof --step round-trip --outcome <passed|failed|skipped>
30
30
  ```
31
31
 
32
32
  Use `passed` only for proved two-client sync, `failed` for an attempted proof that failed,
33
- and `skipped` when the proof could not run. Then run `npx --yes copilotkit@4.12.0 onboard audit`.
33
+ and `skipped` when the proof could not run. Then run `npx --yes copilotkit@4.13.1 onboard audit`.
34
34
  Continue only when it starts with `Status: passed`.
35
35
 
36
36
  If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -45,8 +45,8 @@ Run the audit again after each accepted or authorized change.
45
45
  If the audit still fails, or starts with `Status: blocked`, route out and stop:
46
46
 
47
47
  ```text
48
- npx --yes copilotkit@4.12.0 onboard read feature/stop
48
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
49
49
  ```
50
50
 
51
51
  When the audit passes, run
52
- `npx --yes copilotkit@4.12.0 onboard read feature/complete` with the actual outcome.
52
+ `npx --yes copilotkit@4.13.1 onboard read feature/complete` with the actual outcome.
@@ -7,7 +7,7 @@ two-context proof to subagents within the target project.
7
7
  Before any subagent or project process runs, capture the developer's existing work:
8
8
 
9
9
  ```text
10
- npx --yes copilotkit@4.12.0 onboard protect
10
+ npx --yes copilotkit@4.13.1 onboard protect
11
11
  ```
12
12
 
13
13
  Keep the exact protected path list it prints and give that list to every subagent. No
@@ -23,7 +23,7 @@ unchanged and direct the developer to generic onboarding first.
23
23
  Wait for the inspection subagent to finish. Then report that the inspection came back:
24
24
 
25
25
  ```text
26
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase research-returned
26
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase research-returned
27
27
  ```
28
28
 
29
29
  A refused checkpoint prints its reason and leaves onboarding unaffected. It is not a
@@ -33,7 +33,7 @@ If the inspection did not prove the baseline this intent extends, stop here with
33
33
  changing files:
34
34
 
35
35
  ```text
36
- npx --yes copilotkit@4.12.0 onboard read feature/stop
36
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
37
37
  ```
38
38
 
39
39
  Fetch the current official guides before planning:
@@ -59,7 +59,7 @@ one.
59
59
  After approval, record each approved path before implementation:
60
60
 
61
61
  ```text
62
- npx --yes copilotkit@4.12.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
62
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
63
63
  ```
64
64
 
65
65
  If an approved path changed after capture and no implementation step has run, add
@@ -69,7 +69,7 @@ authorize a path the approved plan did not list.
69
69
  Then report the plan this run is about to implement:
70
70
 
71
71
  ```text
72
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase plan-written
72
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase plan-written
73
73
  ```
74
74
 
75
- Then run `npx --yes copilotkit@4.12.0 onboard read feature/realtime-sync/implement`.
75
+ Then run `npx --yes copilotkit@4.13.1 onboard read feature/realtime-sync/implement`.
@@ -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 --yes copilotkit@4.12.0 login --json` and follow its single streaming session. Then
5
+ `npx --yes copilotkit@4.13.1 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
@@ -20,14 +20,14 @@ non-zero on an app that is working. Pass what `identifyUser` reads with a repeat
20
20
  It is not a defect to repair.
21
21
 
22
22
  Run focused type/test commands, then start the app and run
23
- `npx --yes copilotkit@4.12.0 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
23
+ `npx --yes copilotkit@4.13.1 verify --expect-runtime intelligence --round-trip --agent <agent-id> --json`.
24
24
  Repair changed-file failures before continuing. Record changed paths and secret-safe
25
25
  validation evidence.
26
26
 
27
27
  After validation and each repair, run:
28
28
 
29
29
  ```text
30
- npx --yes copilotkit@4.12.0 onboard audit
30
+ npx --yes copilotkit@4.13.1 onboard audit
31
31
  ```
32
32
 
33
33
  Continue only when it starts with `Status: passed`. A path under `Authorized to modify:` is
@@ -38,7 +38,7 @@ with the implementation subagent's `Files changed` section. If that section does
38
38
  the path, accept the developer's external change:
39
39
 
40
40
  ```text
41
- npx --yes copilotkit@4.12.0 onboard protect --accept-external --path <path>
41
+ npx --yes copilotkit@4.13.1 onboard protect --accept-external --path <path>
42
42
  ```
43
43
 
44
44
  For an env file where the developer placed a requested credential, use
@@ -47,24 +47,24 @@ or its report does not settle who changed it, ask the developer to allow the unp
47
47
  change. Only after they agree, record their answer:
48
48
 
49
49
  ```text
50
- npx --yes copilotkit@4.12.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
50
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
51
51
  ```
52
52
 
53
53
  Run the audit again after each accepted or authorized change. If it still fails, or starts
54
54
  with `Status: blocked`, route out and stop:
55
55
 
56
56
  ```text
57
- npx --yes copilotkit@4.12.0 onboard read feature/stop
57
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
58
58
  ```
59
59
 
60
60
  When implementation validation passes, report it:
61
61
 
62
62
  ```text
63
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase build-validated
63
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase build-validated
64
64
  ```
65
65
 
66
66
  If validation cannot pass, or this intent needs a prerequisite the app does not have, use
67
67
  the feature stop route above without further changes.
68
68
 
69
69
  Otherwise run
70
- `npx --yes copilotkit@4.12.0 onboard read feature/rich-threads/proof`.
70
+ `npx --yes copilotkit@4.13.1 onboard read feature/rich-threads/proof`.
@@ -13,24 +13,24 @@ running.
13
13
  Report each attempt at the proof as it ends, counting from one:
14
14
 
15
15
  ```text
16
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase journey-attempted --attempt 1
16
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase journey-attempted --attempt 1
17
17
  ```
18
18
 
19
19
  Report each repair cycle the same way, counting from one:
20
20
 
21
21
  ```text
22
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase repair-attempted --attempt 1
22
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase repair-attempted --attempt 1
23
23
  ```
24
24
 
25
25
  After the final attempt, report the gate exactly once:
26
26
 
27
27
  ```text
28
- npx --yes copilotkit@4.12.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
28
+ npx --yes copilotkit@4.13.1 onboard proof --step round-trip --outcome <passed|failed|skipped>
29
29
  ```
30
30
 
31
31
  Use `passed` only for proved persistence and reopen, `failed` for an attempted proof that
32
32
  failed, and `skipped` when the proof could not run. Then run
33
- `npx --yes copilotkit@4.12.0 onboard audit`. Continue only when it starts with
33
+ `npx --yes copilotkit@4.13.1 onboard audit`. Continue only when it starts with
34
34
  `Status: passed`.
35
35
 
36
36
  If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -45,9 +45,9 @@ Run the audit again after each accepted or authorized change.
45
45
  If the audit still fails, or starts with `Status: blocked`, route out and stop:
46
46
 
47
47
  ```text
48
- npx --yes copilotkit@4.12.0 onboard read feature/stop
48
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
49
49
  ```
50
50
 
51
51
  When the audit passes, run
52
- `npx --yes copilotkit@4.12.0 onboard read feature/complete` with the actual browser
52
+ `npx --yes copilotkit@4.13.1 onboard read feature/complete` with the actual browser
53
53
  outcome.
@@ -7,7 +7,7 @@ implementation, and proof to separate subagents within the target project.
7
7
  Before any subagent or project process runs, capture the developer's existing work:
8
8
 
9
9
  ```text
10
- npx --yes copilotkit@4.12.0 onboard protect
10
+ npx --yes copilotkit@4.13.1 onboard protect
11
11
  ```
12
12
 
13
13
  Keep the exact protected path list it prints and give that list to every subagent. No
@@ -23,7 +23,7 @@ an existing CopilotKit app, leave it unchanged and direct the developer to gener
23
23
  Wait for the inspection subagent to finish. Then report that the inspection came back:
24
24
 
25
25
  ```text
26
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase research-returned
26
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase research-returned
27
27
  ```
28
28
 
29
29
  A refused checkpoint prints its reason and leaves onboarding unaffected. It is not a
@@ -33,7 +33,7 @@ If the inspection did not prove the baseline this intent extends, stop here with
33
33
  changing files:
34
34
 
35
35
  ```text
36
- npx --yes copilotkit@4.12.0 onboard read feature/stop
36
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
37
37
  ```
38
38
 
39
39
  Fetch the current official guides before planning:
@@ -61,7 +61,7 @@ one.
61
61
  After approval, record each approved path before implementation:
62
62
 
63
63
  ```text
64
- npx --yes copilotkit@4.12.0 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
64
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --path <path> --reason "<the plan's sentence>"
65
65
  ```
66
66
 
67
67
  If an approved path changed after capture and no implementation step has run, add
@@ -71,7 +71,7 @@ authorize a path the approved plan did not list.
71
71
  Then report the plan this run is about to implement:
72
72
 
73
73
  ```text
74
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase plan-written
74
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase plan-written
75
75
  ```
76
76
 
77
- Then run `npx --yes copilotkit@4.12.0 onboard read feature/rich-threads/implement`.
77
+ Then run `npx --yes copilotkit@4.13.1 onboard read feature/rich-threads/implement`.
@@ -20,7 +20,7 @@ a `start` with no `--run` reprints the id this stopped run already holds, and on
20
20
  covering both reads as one run that did two different things.
21
21
 
22
22
  ```text
23
- npx --yes copilotkit@4.12.0 onboard start --run <new-12-character-id>
23
+ npx --yes copilotkit@4.13.1 onboard start --run <new-12-character-id>
24
24
  ```
25
25
 
26
26
  Do not read a generic onboarding node from this run. A feature run and a generic run are
@@ -35,7 +35,7 @@ Send one short report. Run the friction command without another developer questi
35
35
  ask the developer about telemetry: the command applies the setting they already have.
36
36
 
37
37
  ```text
38
- npx --yes copilotkit@4.12.0 onboard friction --phase stop --category <slug>
38
+ npx --yes copilotkit@4.13.1 onboard friction --phase stop --category <slug>
39
39
  ```
40
40
 
41
41
  Write one or two sentences to standard input: the step you stopped at and what stopped it.
@@ -14,7 +14,7 @@ voice proof. Record changed paths and validation results.
14
14
  After validation and each repair, run:
15
15
 
16
16
  ```text
17
- npx --yes copilotkit@4.12.0 onboard audit
17
+ npx --yes copilotkit@4.13.1 onboard audit
18
18
  ```
19
19
 
20
20
  Continue only when it starts with `Status: passed`. A path under `Authorized to modify:` is
@@ -25,7 +25,7 @@ with the implementation subagent's `Files changed` section. If that section does
25
25
  the path, accept the developer's external change:
26
26
 
27
27
  ```text
28
- npx --yes copilotkit@4.12.0 onboard protect --accept-external --path <path>
28
+ npx --yes copilotkit@4.13.1 onboard protect --accept-external --path <path>
29
29
  ```
30
30
 
31
31
  For an env file where the developer placed a requested credential, use
@@ -34,24 +34,24 @@ or its report does not settle who changed it, ask the developer to allow the unp
34
34
  change. Only after they agree, record their answer:
35
35
 
36
36
  ```text
37
- npx --yes copilotkit@4.12.0 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
37
+ npx --yes copilotkit@4.13.1 onboard protect --authorize --unplanned --path <path> --reason "<what the developer said>"
38
38
  ```
39
39
 
40
40
  Run the audit again after each accepted or authorized change. If it still fails, or starts
41
41
  with `Status: blocked`, route out and stop:
42
42
 
43
43
  ```text
44
- npx --yes copilotkit@4.12.0 onboard read feature/stop
44
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
45
45
  ```
46
46
 
47
47
  When implementation validation passes, report it:
48
48
 
49
49
  ```text
50
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase build-validated
50
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase build-validated
51
51
  ```
52
52
 
53
53
  If validation cannot pass, or this intent needs a prerequisite the app does not have, use
54
54
  the feature stop route above without further changes.
55
55
 
56
56
  Otherwise run
57
- `npx --yes copilotkit@4.12.0 onboard read feature/voice/proof`.
57
+ `npx --yes copilotkit@4.13.1 onboard read feature/voice/proof`.
@@ -13,23 +13,23 @@ path, agent response, app URL, and process IDs. Fix changed-file defects and rep
13
13
  Report each attempt at the proof as it ends, counting from one:
14
14
 
15
15
  ```text
16
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase journey-attempted --attempt 1
16
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase journey-attempted --attempt 1
17
17
  ```
18
18
 
19
19
  Report each repair cycle the same way, counting from one:
20
20
 
21
21
  ```text
22
- npx --yes copilotkit@4.12.0 onboard checkpoint --phase repair-attempted --attempt 1
22
+ npx --yes copilotkit@4.13.1 onboard checkpoint --phase repair-attempted --attempt 1
23
23
  ```
24
24
 
25
25
  After the final attempt, report the gate exactly once:
26
26
 
27
27
  ```text
28
- npx --yes copilotkit@4.12.0 onboard proof --step round-trip --outcome <passed|failed|skipped>
28
+ npx --yes copilotkit@4.13.1 onboard proof --step round-trip --outcome <passed|failed|skipped>
29
29
  ```
30
30
 
31
31
  Use `passed` only for proved voice input, `failed` for an attempted proof that failed, and
32
- `skipped` when the proof could not run. Then run `npx --yes copilotkit@4.12.0 onboard audit`.
32
+ `skipped` when the proof could not run. Then run `npx --yes copilotkit@4.13.1 onboard audit`.
33
33
  Continue only when it starts with `Status: passed`.
34
34
 
35
35
  If the audit fails, never repair, reset, or revert a protected path. Compare each named path
@@ -44,9 +44,9 @@ Run the audit again after each accepted or authorized change.
44
44
  If the audit still fails, or starts with `Status: blocked`, route out and stop:
45
45
 
46
46
  ```text
47
- npx --yes copilotkit@4.12.0 onboard read feature/stop
47
+ npx --yes copilotkit@4.13.1 onboard read feature/stop
48
48
  ```
49
49
 
50
50
  When the audit passes, run
51
- `npx --yes copilotkit@4.12.0 onboard read feature/complete` with the actual surface
51
+ `npx --yes copilotkit@4.13.1 onboard read feature/complete` with the actual surface
52
52
  outcome.