@autonoma-ai/planner 0.1.28 → 0.1.30-canary.00be409
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 +8 -3
- package/dist/index.js +3898 -1713
- package/dist/index.js.map +1 -1
- package/package.json +4 -4
package/README.md
CHANGED
|
@@ -37,7 +37,7 @@ Requires **Node.js >= 22.13**. Autonoma shows you this command when you connect
|
|
|
37
37
|
your token and ids already filled in. Open a terminal in your project and paste it:
|
|
38
38
|
|
|
39
39
|
```bash
|
|
40
|
-
AUTONOMA_API_TOKEN
|
|
40
|
+
AUTONOMA_API_TOKEN=<api-token> AUTONOMA_GENERATION_ID=<generation-id> AUTONOMA_APPLICATION_ID=<application-id> \
|
|
41
41
|
npx @autonoma-ai/planner@latest
|
|
42
42
|
```
|
|
43
43
|
|
|
@@ -69,7 +69,7 @@ npx @autonoma-ai/planner@latest status
|
|
|
69
69
|
|
|
70
70
|
# Re-send everything already generated on disk. Idempotent, and the fix when a run
|
|
71
71
|
# finished but an artifact did not arrive. Needs the same env vars as a run.
|
|
72
|
-
AUTONOMA_API_TOKEN
|
|
72
|
+
AUTONOMA_API_TOKEN=<api-token> AUTONOMA_GENERATION_ID=<generation-id> \
|
|
73
73
|
npx @autonoma-ai/planner@latest upload
|
|
74
74
|
|
|
75
75
|
# Every flag, and what each step of the run does.
|
|
@@ -118,6 +118,11 @@ Steps 1 and 7 hand the terminal to your **locally installed coding agent** (Clau
|
|
|
118
118
|
CLI) the way `git commit` opens your editor - the dashboard steps aside, and control comes back
|
|
119
119
|
when the agent exits.
|
|
120
120
|
|
|
121
|
+
Claude Code is started on Opus, for its own session and for any subagent it spawns, rather than on
|
|
122
|
+
whatever model your plan happens to hand it. These two steps install the SDK, boot your app and
|
|
123
|
+
validate it against a live environment, and a weaker model there fails in ways that read as your
|
|
124
|
+
app being broken.
|
|
125
|
+
|
|
121
126
|
<p align="center">
|
|
122
127
|
<img src="https://docs.autonoma.app/img/test-planner/tui-handoff.png" alt="The planner's terminal just before the handoff: a modal over the dimmed dashboard badged UP NEXT, headed 'Handing off to Claude Code', explaining that the terminal is about to switch and that you come straight back afterwards, with a footer reading 'Continuing in 10s - enter continue now'" width="100%">
|
|
123
128
|
</p>
|
|
@@ -168,7 +173,7 @@ a standalone run.
|
|
|
168
173
|
|
|
169
174
|
| Variable | Required | Purpose |
|
|
170
175
|
| --- | --- | --- |
|
|
171
|
-
| `AUTONOMA_API_TOKEN` | yes | The run's credential. It runs on managed Autonoma credits through our LLM proxy, so no LLM key is needed. Create one under **Settings → API keys**. |
|
|
176
|
+
| `AUTONOMA_API_TOKEN` | yes | The run's credential. It runs on managed Autonoma credits through our LLM proxy, so no LLM key is needed. Create one under **Settings → API keys**. A stand-in copied out of a snippet (`...`, `<api-token>`, `YOUR_TOKEN`) is rejected before the run starts. |
|
|
172
177
|
| `AUTONOMA_APPLICATION_ID` | no | The app this run belongs to. With it the run also sets up the preview environment and validates the result; without it the planner runs standalone against any repo. |
|
|
173
178
|
| `AUTONOMA_GENERATION_ID` | for upload | The setup its artifacts are uploaded against. |
|
|
174
179
|
| `AUTONOMA_SHARED_SECRET` | no | Signs the SDK and webhook requests the run makes on your behalf. |
|