copilotkit 4.14.0 → 4.15.0
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.
- package/README.md +41 -6
- package/cli-build-info.json +8 -8
- package/index.js +31335 -30607
- package/onboarding/index.json +1 -1
- package/onboarding/prompts/authenticate/start.md +17 -8
- package/onboarding/prompts/conversion/plan.md +3 -3
- package/onboarding/prompts/credentials/finalize-plan.md +8 -8
- package/onboarding/prompts/credentials/plan.md +21 -21
- package/onboarding/prompts/credentials/settle-credentials.md +10 -10
- package/onboarding/prompts/credentials/write-plan.md +6 -6
- package/onboarding/prompts/fallback/best-effort.md +7 -7
- package/onboarding/prompts/feature/a2ui/implement.md +6 -6
- package/onboarding/prompts/feature/a2ui/proof.md +6 -6
- package/onboarding/prompts/feature/a2ui/start.md +7 -7
- package/onboarding/prompts/feature/channels/implement.md +7 -7
- package/onboarding/prompts/feature/channels/proof.md +6 -6
- package/onboarding/prompts/feature/channels/start.md +7 -7
- package/onboarding/prompts/feature/chat-suggestions/implement.md +6 -6
- package/onboarding/prompts/feature/chat-suggestions/proof.md +6 -6
- package/onboarding/prompts/feature/chat-suggestions/start.md +7 -7
- package/onboarding/prompts/feature/complete.md +3 -3
- package/onboarding/prompts/feature/learning/implement.md +16 -16
- package/onboarding/prompts/feature/learning/proof.md +7 -7
- package/onboarding/prompts/feature/learning/start.md +9 -9
- package/onboarding/prompts/feature/open-generative-ui/implement.md +6 -6
- package/onboarding/prompts/feature/open-generative-ui/proof.md +6 -6
- package/onboarding/prompts/feature/open-generative-ui/start.md +7 -7
- package/onboarding/prompts/feature/realtime-sync/implement.md +7 -7
- package/onboarding/prompts/feature/realtime-sync/proof.md +6 -6
- package/onboarding/prompts/feature/realtime-sync/start.md +6 -6
- package/onboarding/prompts/feature/rich-threads/implement.md +8 -8
- package/onboarding/prompts/feature/rich-threads/proof.md +6 -6
- package/onboarding/prompts/feature/rich-threads/start.md +6 -6
- package/onboarding/prompts/feature/stop.md +5 -5
- package/onboarding/prompts/feature/voice/implement.md +6 -6
- package/onboarding/prompts/feature/voice/proof.md +6 -6
- package/onboarding/prompts/feature/voice/start.md +7 -7
- package/onboarding/prompts/framework/ag2.md +2 -2
- package/onboarding/prompts/framework/agno.md +2 -2
- package/onboarding/prompts/framework/built-in.md +2 -2
- package/onboarding/prompts/framework/claude-sdk-python.md +2 -2
- package/onboarding/prompts/framework/claude-sdk-typescript.md +2 -2
- package/onboarding/prompts/framework/crewai-flows.md +2 -2
- package/onboarding/prompts/framework/deep-agents.md +2 -2
- package/onboarding/prompts/framework/google-adk.md +2 -2
- package/onboarding/prompts/framework/langgraph-fastapi.md +2 -2
- package/onboarding/prompts/framework/langgraph-python.md +2 -2
- package/onboarding/prompts/framework/langgraph-typescript.md +2 -2
- package/onboarding/prompts/framework/llamaindex.md +2 -2
- package/onboarding/prompts/framework/mastra.md +2 -2
- package/onboarding/prompts/framework/ms-agent-dotnet.md +2 -2
- package/onboarding/prompts/framework/ms-agent-harness-dotnet.md +2 -2
- package/onboarding/prompts/framework/ms-agent-python.md +2 -2
- package/onboarding/prompts/framework/pydantic-ai.md +2 -2
- package/onboarding/prompts/framework/strands-python.md +2 -2
- package/onboarding/prompts/framework/strands-typescript.md +2 -2
- package/onboarding/prompts/frontend/angular.md +3 -3
- package/onboarding/prompts/frontend/nextjs.md +3 -3
- package/onboarding/prompts/frontend/plan.md +7 -7
- package/onboarding/prompts/frontend/react-native.md +2 -2
- package/onboarding/prompts/frontend/react-spa.md +2 -2
- package/onboarding/prompts/frontend/vue.md +2 -2
- package/onboarding/prompts/implementation/build-and-validate.md +16 -16
- package/onboarding/prompts/proof/complete.md +9 -9
- package/onboarding/prompts/proof/oss-baseline.md +5 -5
- package/onboarding/prompts/proof/round-trip.md +11 -11
- package/onboarding/prompts/research/gather.md +6 -6
- package/onboarding/prompts/research/merge.md +3 -3
- package/onboarding/prompts/research/preflight.md +4 -4
- package/onboarding/prompts/research/route.md +5 -5
- package/onboarding/prompts/starter/clone.md +6 -6
- package/onboarding/prompts/stopped/run-failed.md +4 -4
- package/onboarding/prompts/subagent/create-plan.md +1 -1
- package/onboarding/prompts/subagent/inspect-repository.md +1 -1
- package/onboarding/prompts/subagent/prove-oss-baseline.md +8 -1
- package/onboarding/prompts/subagent/prove-round-trip.md +18 -16
- package/onboarding/prompts/unsupported/no-validated-path.md +3 -3
- package/package.json +1 -1
- package/release/release-tool.js +1 -1
|
@@ -170,7 +170,7 @@ here is work the developer did not ask for.
|
|
|
170
170
|
Plan the threads drawer itself: add it from the selected drawer page, where this frontend
|
|
171
171
|
does not already render one. Where this journey's frontend framework ships no threads
|
|
172
172
|
drawer -- React Native --, plan that the thread is proved by
|
|
173
|
-
`npx --yes copilotkit@4.
|
|
173
|
+
`npx --prefer-offline --yes copilotkit@4.15.0 verify --round-trip`, which needs no browser. Do not plan a
|
|
174
174
|
step that opens the managed Intelligence dashboard.
|
|
175
175
|
|
|
176
176
|
## Order the plan into steps
|
|
@@ -7,7 +7,7 @@ Work only on the packet you were assigned. Inspect the repository without changi
|
|
|
7
7
|
Run this first, from the target project directory:
|
|
8
8
|
|
|
9
9
|
```text
|
|
10
|
-
npx --yes copilotkit@4.
|
|
10
|
+
npx --prefer-offline --yes copilotkit@4.15.0 onboard inspect --json
|
|
11
11
|
```
|
|
12
12
|
|
|
13
13
|
It answers the deterministic half of both packets exactly, from the same code
|
|
@@ -7,6 +7,13 @@ Find the expected agent id from the project. Start the existing agent and fronte
|
|
|
7
7
|
when they are not already running. Before using a port, identify its process and working
|
|
8
8
|
directory. Do not stop a process outside this project.
|
|
9
9
|
|
|
10
|
+
If your harness runs commands in a sandbox, a sandboxed command cannot listen on a port or
|
|
11
|
+
connect to localhost. Before the first server start, request escalation with a prefix rule
|
|
12
|
+
for the project's own dev script. Before the first request to a local server, request
|
|
13
|
+
escalation with a prefix rule for `curl`. If a local request still fails after 0 ms
|
|
14
|
+
(`Failed to connect ... after 0 ms`) while the port shows a listener, the sandbox blocked
|
|
15
|
+
it. Run it again with escalation, and do not record a failed predicate or step.
|
|
16
|
+
|
|
10
17
|
Prove the live runtime in this order:
|
|
11
18
|
|
|
12
19
|
1. GET `/info` from the project's CopilotKit runtime and require a valid response.
|
|
@@ -19,7 +26,7 @@ Prove the live runtime in this order:
|
|
|
19
26
|
4. Confirm from project files that the runtime constructor passes a `runner` option rather
|
|
20
27
|
than an `intelligence` option. A package, import, project file, or key is not use proof.
|
|
21
28
|
5. Run
|
|
22
|
-
`npx --yes copilotkit@4.
|
|
29
|
+
`npx --prefer-offline --yes copilotkit@4.15.0 verify --expect-runtime oss --round-trip --agent <expected-agent-id> --json`,
|
|
23
30
|
with the runtime URL or auth header options that this project needs. Require exit zero
|
|
24
31
|
and the JSON `ok` field to be `true`.
|
|
25
32
|
6. Drive one real request through the existing frontend, CopilotKit runtime, and expected
|
|
@@ -89,21 +89,23 @@ agent and the frontend from one `dev` script, which runs them under
|
|
|
89
89
|
other. A second start against a project already running that script collides with a server
|
|
90
90
|
that is up.
|
|
91
91
|
|
|
92
|
+
If your harness runs commands in a sandbox, a sandboxed command cannot listen on a port or
|
|
93
|
+
connect to localhost. Before the first server start, request escalation with a prefix rule
|
|
94
|
+
for the project's own dev script. Before the first request to a local server, request
|
|
95
|
+
escalation with a prefix rule for `curl`. If a local request still fails after 0 ms
|
|
96
|
+
(`Failed to connect ... after 0 ms`) while the port shows a listener, the sandbox blocked
|
|
97
|
+
it. Run it again with escalation, and do not record a failed predicate or step.
|
|
98
|
+
|
|
92
99
|
Start each server in the background with the project's own script. Then wait for it to
|
|
93
100
|
answer rather than for a fixed number of seconds:
|
|
94
101
|
|
|
95
102
|
```bash
|
|
96
|
-
|
|
97
|
-
for _ in $(seq 90); do
|
|
98
|
-
curl -fs -o /dev/null "<url>" && ready=1 && break
|
|
99
|
-
sleep 1
|
|
100
|
-
done
|
|
101
|
-
[ "$ready" = 1 ] && echo "up" || echo "no answer from <url> after 90 seconds"
|
|
103
|
+
curl -fs -o /dev/null --retry 90 --retry-delay 1 --retry-max-time 90 --retry-all-errors "<url>"
|
|
102
104
|
```
|
|
103
105
|
|
|
104
|
-
|
|
105
|
-
A server that never answered has written the reason to its own output, and
|
|
106
|
-
output is faster than starting it again.
|
|
106
|
+
A zero exit means the server answered. Any other exit means that it did not answer in 90
|
|
107
|
+
seconds. A server that never answered has written the reason to its own output, and
|
|
108
|
+
reading that output is faster than starting it again.
|
|
107
109
|
|
|
108
110
|
That coupling also turns an ordinary restart into a false failure. Where you stop a server
|
|
109
111
|
to pick up an installed dependency, start both again and wait for both to answer before you
|
|
@@ -145,7 +147,7 @@ IPv6 only, so an IPv4 literal fails against the correct port.
|
|
|
145
147
|
## Step 4 -- Check the wiring
|
|
146
148
|
|
|
147
149
|
With both running, check the wiring in one command before you open a browser:
|
|
148
|
-
`npx --yes copilotkit@4.
|
|
150
|
+
`npx --prefer-offline --yes copilotkit@4.15.0 verify --json`. It reads the port from this project, so a
|
|
149
151
|
non-default port needs no flag. The payload reports `runtimeUrl` and `runtimeUrlSource`. A
|
|
150
152
|
`runtimeUrlSource` of `default` means nothing in the project named a port, so pass
|
|
151
153
|
`--runtime-url` with the URL from step 1 in that case. Read the individual checks rather than
|
|
@@ -179,7 +181,7 @@ named no port the CLI can read: keep step 2's URL, and rewrite its host as `loca
|
|
|
179
181
|
before you use it.
|
|
180
182
|
|
|
181
183
|
Then run the command once more with the URL you are about to open:
|
|
182
|
-
`npx --yes copilotkit@4.
|
|
184
|
+
`npx --prefer-offline --yes copilotkit@4.15.0 verify --frontend-url <that url> --json`. The
|
|
183
185
|
`frontend_assets_served` check asks that server for its page and for one of the page's own
|
|
184
186
|
assets, on that exact host. A `fail` there means the dev server refuses its own static
|
|
185
187
|
assets on the host you were about to use, and the check names the URL to use instead. This
|
|
@@ -187,7 +189,7 @@ is the cheapest step that can save the most expensive one, so run it before the
|
|
|
187
189
|
|
|
188
190
|
## Step 5 -- Prove that the agent runs
|
|
189
191
|
|
|
190
|
-
Run `npx --yes copilotkit@4.
|
|
192
|
+
Run `npx --prefer-offline --yes copilotkit@4.15.0 verify --round-trip --json`. It sends one request through
|
|
191
193
|
the runtime and reads the answer back from the thread, so it separates an agent that is
|
|
192
194
|
configured from an agent that works. Use `--agent <id>` when the runtime declares more
|
|
193
195
|
than one. If it reports `user-not-identified`, this project's `identifyUser` reads a
|
|
@@ -200,7 +202,7 @@ Where this run settled a Learning Container, add the flag to the call above rath
|
|
|
200
202
|
running a second round trip:
|
|
201
203
|
|
|
202
204
|
```text
|
|
203
|
-
npx --yes copilotkit@4.
|
|
205
|
+
npx --prefer-offline --yes copilotkit@4.15.0 verify --round-trip --expect-learning-container <container id> --json
|
|
204
206
|
```
|
|
205
207
|
|
|
206
208
|
The check reads the thread that this run created, so a second round trip proves a second
|
|
@@ -234,7 +236,7 @@ the credential was written holds an empty key while the file beside it carries t
|
|
|
234
236
|
one. Run this from the target app directory:
|
|
235
237
|
|
|
236
238
|
```text
|
|
237
|
-
npx --yes copilotkit@4.
|
|
239
|
+
npx --prefer-offline --yes copilotkit@4.15.0 onboard env-staleness
|
|
238
240
|
```
|
|
239
241
|
|
|
240
242
|
A `stale` line names the env file and how long after launch it was written. Report that,
|
|
@@ -312,7 +314,7 @@ For a recorded `both-oss` starting state, this step has no component to render.
|
|
|
312
314
|
same request the baseline recorded, require the same kind of user-visible result the
|
|
313
315
|
baseline produced, and require that the thread for that request is listed in the drawer.
|
|
314
316
|
Where this journey's frontend framework ships no threads drawer -- React Native --, prove
|
|
315
|
-
that thread with `npx --yes copilotkit@4.
|
|
317
|
+
that thread with `npx --prefer-offline --yes copilotkit@4.15.0 verify --round-trip`, which reads the
|
|
316
318
|
answer back off the thread and needs no browser. Record which of the two you proved.
|
|
317
319
|
|
|
318
320
|
Use the surface control the main coding agent recorded for your environment. It either had
|
|
@@ -340,7 +342,7 @@ request never exercises. Drive it with the browser control step 6 named.
|
|
|
340
342
|
the page to finish loading. Do not retype the host, and do not substitute a URL a tool
|
|
341
343
|
offers you by default. Where the page loads but its styling is missing or the chat
|
|
342
344
|
control is dead, run
|
|
343
|
-
`npx --yes copilotkit@4.
|
|
345
|
+
`npx --prefer-offline --yes copilotkit@4.15.0 verify --frontend-url <the url you opened> --json`
|
|
344
346
|
before you diagnose anything else. A dev server can serve its page and refuse every
|
|
345
347
|
static chunk behind it, and on screen that is indistinguishable from a broken
|
|
346
348
|
integration. The `frontend_assets_served` check tells the two apart.
|
|
@@ -30,16 +30,16 @@ Before you show the best-effort plan, require this complete packet:
|
|
|
30
30
|
- Give the ordered proof rules.
|
|
31
31
|
|
|
32
32
|
After the developer approves the best-effort plan, run
|
|
33
|
-
`npx --yes copilotkit@4.
|
|
33
|
+
`npx --prefer-offline --yes copilotkit@4.15.0 onboard read fallback/best-effort`.
|
|
34
34
|
|
|
35
35
|
Send one short report. Run the friction command without another developer question. Do not
|
|
36
36
|
ask the developer about telemetry: the command applies the setting they already have.
|
|
37
37
|
|
|
38
38
|
```text
|
|
39
|
-
npx --yes copilotkit@4.
|
|
39
|
+
npx --prefer-offline --yes copilotkit@4.15.0 onboard friction --phase stop --category <slug> --message "<sentences>"
|
|
40
40
|
```
|
|
41
41
|
|
|
42
|
-
|
|
42
|
+
`--message` takes one or two sentences: the step you stopped at and what stopped it.
|
|
43
43
|
Pick the category that fits from docs-missing, docs-wrong, docs-sequential, cli-gap,
|
|
44
44
|
sdk-gap, environment, port-collision, credential, validation-loop, and other. Leave
|
|
45
45
|
--cost-seconds off. A run that stopped cannot separate one papercut's cost from the cost
|
package/package.json
CHANGED
package/release/release-tool.js
CHANGED
|
@@ -14811,7 +14811,7 @@ var FLAG_DEFINITIONS = defineFlags({
|
|
|
14811
14811
|
|
|
14812
14812
|
// apps/cli/src/config.ts
|
|
14813
14813
|
function getTemplateRef() {
|
|
14814
|
-
return true ? "
|
|
14814
|
+
return true ? "33db9a81ccfd2d6e820defe3c1616594909439af" : "main";
|
|
14815
14815
|
}
|
|
14816
14816
|
|
|
14817
14817
|
// apps/cli/src/services/agentcore-config.ts
|