fix(ci): repair PR-Agent model routing
PR Check / Security scan (Snyk) (pull_request) Skipped
PR Check / Lint + typecheck (pull_request) Successful in 1m8s
PR Check / Secret scan (gitleaks) (pull_request) Successful in 7s
PR Check / Dependency audit (pull_request) Successful in 8s
PR Check / Dockerfile lint (droast) (pull_request) Successful in 5s

OpenCode Go rejects requests without x-opencode-session, and LiteLLM needs the openai/ prefix on the fallback model. Supply the header through LITELLM__EXTRA_HEADERS, keep the prefixed fallback, and stop auto-running /improve so a PR gets one review plus /describe.
This commit is contained in:
Noel Sabia committed 2026-10-30 21:14:15 +01:00
1 parent 3eac73255f
commit a43134ad83
4 files changed
+25 -3

No files matched your search

+7 -1
View File
@@ -15,6 +15,10 @@ endpoint is not published to the internet.
| Status | `ssh … agent@server0 status` |
| Upgrade | edit the root-owned compose file, then run `deploy` |
The table describes the target state. The live stack is still at
`/home/noel/self-hosted/pr-agent` and is managed with `noel`'s SSH key until
`setup-agent-access.sh` has been run.
## Gitea side
1. The bot user `pr-agent` is a collaborator on `CV_Website/CV_Site_Nuxt` with
@@ -85,7 +89,9 @@ sudo /usr/local/sbin/pr-agent-deploy
Open a pull request in `CV_Website/CV_Site_Nuxt`. The server runs `/describe`
and `/review` on open/reopen; comment commands such as `/review`, `/improve`
and `/ask` are handled from the PR conversation. If nothing appears:
and `/ask` are handled from the PR conversation. `/improve` is deliberately
on demand: adding it to the auto list would make a second model call and a
second comment for every PR. If nothing appears:
```sh
ssh -i ~/.ssh/pr_agent_control -o IdentitiesOnly=yes agent@91.99.207.62 logs