111 lines
3.3 KiB
Markdown
111 lines
3.3 KiB
Markdown
# Session: 2026-03-03 22:38:47 UTC
|
||
|
||
- **Session Key**: agent:main:main
|
||
- **Session ID**: f4588213-7254-4bc1-a237-987798220199
|
||
- **Source**: gateway:sessions.reset
|
||
|
||
## Conversation Summary
|
||
|
||
user: Sender (untrusted metadata):
|
||
```json
|
||
{
|
||
"label": "openclaw-tui (gateway-client)",
|
||
"id": "gateway-client",
|
||
"name": "openclaw-tui",
|
||
"username": "openclaw-tui"
|
||
}
|
||
```
|
||
|
||
[Tue 2026-03-03 22:27 UTC] Test openai/gpt-5.2 with litellm API, curl it. Use the already configured litellm API key
|
||
assistant: [[reply_to_current]] Done — tested successfully with your configured `LITELLM_API_KEY`.
|
||
|
||
Used:
|
||
```bash
|
||
BASE_URL="http://192.168.153.113:18804/v1"
|
||
curl -sS "$BASE_URL/chat/completions" \
|
||
-H "Content-Type: application/json" \
|
||
-H "Authorization: Bearer $LITELLM_API_KEY" \
|
||
-d '{"model":"openai/gpt-5.2","messages":[{"role":"user","content":"Reply with exactly: litellm-ok"}],"temperature":0}'
|
||
```
|
||
|
||
Result came back:
|
||
`litellm-ok` (model resolved to `gpt-5.2-2025-12-11`).
|
||
user: Sender (untrusted metadata):
|
||
```json
|
||
{
|
||
"label": "openclaw-tui (gateway-client)",
|
||
"id": "gateway-client",
|
||
"name": "openclaw-tui",
|
||
"username": "openclaw-tui"
|
||
}
|
||
```
|
||
|
||
[Tue 2026-03-03 22:29 UTC] Great. Now let's see why using `/model litellm/gpt-5.2` doesn't work
|
||
assistant: [[reply_to_current]] Nice catch — I just tested it from inside this same session, and `litellm/gpt-5.2` **does resolve now**.
|
||
|
||
I verified by setting the session model via `session_status` override, and it accepted:
|
||
- `Model: litellm/gpt-5.2`
|
||
- auth profile: `litellm:default`
|
||
|
||
So if `/model litellm/gpt-5.2` fails for you, likely causes are:
|
||
|
||
1. **Stale picker/allowlist state** in the current TUI session
|
||
(model was added after the session started).
|
||
|
||
2. **Profile/config mismatch**
|
||
(e.g., TUI connected to a different profile/config than the one we edited).
|
||
|
||
3. **Old slash-command cache** in that client session.
|
||
|
||
Quick checks in your TUI:
|
||
- `/model list` (see if `litellm/gpt-5.2` appears)
|
||
- `/model status` (shows current model + provider info)
|
||
|
||
If it still fails, restart the client/gateway session and retry:
|
||
- `openclaw gateway restart`
|
||
|
||
If you paste the exact `/model` error text, I can pinpoint it immediately.
|
||
user: Sender (untrusted metadata):
|
||
```json
|
||
{
|
||
"label": "openclaw-tui (gateway-client)",
|
||
"id": "gateway-client",
|
||
"name": "openclaw-tui",
|
||
"username": "openclaw-tui"
|
||
}
|
||
```
|
||
|
||
[Tue 2026-03-03 22:37 UTC] test
|
||
user: Sender (untrusted metadata):
|
||
```json
|
||
{
|
||
"label": "openclaw-tui (gateway-client)",
|
||
"id": "gateway-client",
|
||
"name": "openclaw-tui",
|
||
"username": "openclaw-tui"
|
||
}
|
||
```
|
||
|
||
[Tue 2026-03-03 22:37 UTC] model set to litellm/gpt-5.2
|
||
|
||
|
||
test
|
||
|
||
|
||
run error: LLM request timed out.
|
||
assistant: [[reply_to_current]] Yep — that error makes sense given current session size.
|
||
|
||
I just re-tested the LiteLLM endpoint directly with `openai/gpt-5.2`; it responds fast (~1.4s for a tiny prompt), so the model/provider itself is healthy.
|
||
|
||
Most likely cause: your session context is huge, and `gpt-5.2` timed out on a full-context turn.
|
||
|
||
Try this sequence in TUI:
|
||
|
||
1. `/reset`
|
||
2. `/model litellm/gpt-5.2`
|
||
3. Send a tiny prompt: `ping`
|
||
|
||
If that works, timeout was context-related (not model routing).
|
||
|
||
If it still times out after reset, send me the exact `/model status` output and I’ll pinpoint whether it’s a gateway timeout vs LiteLLM upstream timeout.
|