apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-17 15:25:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

Clarify testing: OpenClaw channels vs direct Plano requests

Browse source 
Primary testing is through messaging channels (Telegram, Slack,
etc.) with log monitoring. The test_routing.sh script is now
documented as an optional direct verification tool.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Adil Hafeez 2026-02-17 04:46:26 -08:00
parent 352d60b970
commit 48989eba76
No known key found for this signature in database
GPG key ID: 9B18EF7691369645
1 changed files with 14 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

20
demos/llm_routing/openclaw_routing/README.md
View file

@ -23,7 +23,7 @@ Plano uses a [preference-aligned router](https://arxiv.org/abs/2506.16655) to an
- **Plano CLI**: `uv tool install planoai` or `pip install planoai`
- **OpenClaw**: `npm install -g openclaw@latest`
- **API keys**:
- `MOONSHOT_API_KEY` — from [Moonshot AI](https://platform.moonshot.cn/)
- `MOONSHOT_API_KEY` — from [Moonshot AI](https://www..moonshot.ai/)
- `ANTHROPIC_API_KEY` — from [Anthropic](https://console.anthropic.com/)
## Quick Start
@ -61,17 +61,17 @@ Then run:
openclaw onboard --install-daemon
```
### 4. Test Routing
### 4. Test Routing Through OpenClaw
Run the test script to verify routing decisions:
Send messages through any connected channel (WhatsApp, Telegram, Slack, etc.) and watch routing decisions in a separate terminal:
```bash
bash test_routing.sh
planoai logs --service plano | grep MODEL_RESOLUTION
```
## Demo Scenarios
Try these messages to see routing in action:
| # | Message | Expected Route | Why |
| # | Message (via your messaging channel) | Expected Route | Why |
|---|---------|---------------|-----|
| 1 | "Hey, what's up? Tell me something interesting." | **Kimi K2.5** | General conversation — cheap and fast |
| 2 | "Remind me tomorrow at 9am and ping Slack about the deploy" | **Kimi K2.5** | Agentic multi-step task orchestration |
@ -81,6 +81,14 @@ bash test_routing.sh
OpenClaw's code doesn't change at all. It points at `http://127.0.0.1:12000/v1` instead of a direct provider URL. Plano's router analyzes each prompt and picks the right backend.
### Verify Plano Routing Directly (Optional)
To test Plano's routing without OpenClaw, run the test script which sends requests directly to the gateway:
```bash
bash test_routing.sh
```
## Monitoring
### Routing Decisions