Files
swarm-zap/memory/2026-03-03-litellm-connection-error.md
zap b0b4060bf9 chore(workspace): install all 4 bundled hooks + model default update
- Installed hooks: boot-md, session-memory, command-logger, bootstrap-extra-files
- Updated default model to litellm/copilot-claude-sonnet-4.6
- Added memory/startup-health.json + boot-last-run.json from boot check
- Added memory/startup-health.md warning log
- Captured new session memory files (2026-03-04/05)
- Minor MEMORY.md + USER.md: added git preference line
2026-03-05 04:40:46 +00:00

180 lines
4.6 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

# Session: 2026-03-03 21:18:33 UTC
- **Session Key**: agent:main:main
- **Session ID**: 4e89d280-a179-4c69-ae5f-9d285ffb0f2c
- **Source**: gateway:sessions.reset
## Conversation Summary
user: [Tue 2026-03-03 21:09 UTC] hey
user: [Tue 2026-03-03 21:09 UTC] same
assistant: [[reply_to_current]] Thanks — I found a likely mismatch and patched it:
- Changed LiteLLM provider base URL to include `/v1`:
- `http://192.168.153.113:18804/v1`
This often fixes OpenAI-compatible clients that were otherwise hitting wrong paths and surfacing generic `Connection error`.
Please do:
```bash
openclaw gateway restart
```
Then retest:
1) `model set litellm/claude-haiku-4-5`
2) `hey`
If still failing, Ill do one more hard fix: force model list down to only known-good IDs + strip any dynamic reload leftovers.
user: [Tue 2026-03-03 21:10 UTC] model set to litellm/claude-haiku-4-5 hey run error: Connection error.
user: [Tue 2026-03-03 21:11 UTC] hey
user: [Tue 2026-03-03 21:11 UTC] model set to litellm/claude-haiku-4-5 hey run error: Connection error. model set to litellm/claude-haiku-4-5 hey
assistant: [[reply_to_current]] Youre not crazy — this is now looking like an **OpenClaw-side LiteLLM integration bug** on your current build, not your LiteLLM server.
What we know:
- Direct LiteLLM API call to `claude-haiku-4-5` works (`OK`).
- OpenClaw run with `provider=litellm model=claude-haiku-4-5` repeatedly fails with generic `Connection error`.
- No auth/quota error is surfaced for that model path (unlike Gemini 429s).
### Best next fix (likely)
Youre on **OpenClaw 2026.3.1**, and status keeps showing **update available 2026.3.2**.
Please run:
```bash
openclaw update
openclaw gateway restart
```
Then retest:
```text
model set litellm/claude-haiku-4-5
hey
```
If it still fails after update, Ill do a hard workaround: rewire these models through a custom non-`litellm` provider block (same endpoint/key) so model selection works without the buggy path.
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-tui (gateway-client)",
"id": "gateway-client",
"name": "openclaw-tui",
"username": "openclaw-tui"
}
```
[Tue 2026-03-03 21:14 UTC] hey
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-tui (gateway-client)",
"id": "gateway-client",
"name": "openclaw-tui",
"username": "openclaw-tui"
}
```
[Tue 2026-03-03 21:14 UTC] same issue
assistant: [[reply_to_current]] Got it. Since it still fails, lets bypass the `litellm` provider path entirely.
Use a custom provider name (same LiteLLM endpoint/key), then select models from that provider.
Add this in `~/.openclaw/openclaw.json` under `models.providers`:
```json5
"liteproxy": {
"baseUrl": "http://192.168.153.113:18804/v1",
"apiKey": "sk-3oxoovwm69RyWRREGPJfDQ",
"api": "openai-completions",
"models": [
{ "id": "claude-haiku-4-5", "name": "Claude Haiku 4.5" },
{ "id": "gemini-2.5-flash", "name": "Gemini 2.5 Flash" },
{ "id": "gemini-2.5-flash-lite", "name": "Gemini 2.5 Flash Lite" },
{ "id": "zai-glm-4.7", "name": "GLM 4.7" }
]
}
```
And in `agents.defaults.models` add:
```json5
"liteproxy/claude-haiku-4-5": {},
"liteproxy/gemini-2.5-flash": {},
"liteproxy/gemini-2.5-flash-lite": {},
"liteproxy/zai-glm-4.7": {}
```
Then restart:
```bash
openclaw gateway restart
```
Test:
```text
model set liteproxy/claude-haiku-4-5
hey
```
If you want, I can give you one exact `jq` patch command to apply this automatically.
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-tui (gateway-client)",
"id": "gateway-client",
"name": "openclaw-tui",
"username": "openclaw-tui"
}
```
[Tue 2026-03-03 21:15 UTC] di it please
assistant: [[reply_to_current]] Done ✅ I added `liteproxy` as a separate provider and added its models to `/models`.
I also made a backup:
- `~/.openclaw/openclaw.json.backup-before-liteproxy-20260303T211619Z`
Now run:
```bash
openclaw gateway restart
```
Then test:
```text
model set liteproxy/claude-haiku-4-5
hey
```
If that still fails, paste the exact output and Ill keep debugging live.
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-tui (gateway-client)",
"id": "gateway-client",
"name": "openclaw-tui",
"username": "openclaw-tui"
}
```
[Tue 2026-03-03 21:15 UTC] hey
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-tui (gateway-client)",
"id": "gateway-client",
"name": "openclaw-tui",
"username": "openclaw-tui"
}
```
[Tue 2026-03-03 21:16 UTC] ?
user: Sender (untrusted metadata):
```json
{
"label": "openclaw-tui (gateway-client)",
"id": "gateway-client",
"name": "openclaw-tui",
"username": "openclaw-tui"
}
```
[Tue 2026-03-03 21:16 UTC] same