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 -2
View File
@@ -82,6 +82,9 @@ provider rejects the request before it reaches the model.
* The webhook sends `push`, `issues`, `pull_request` and `issue_comment`
events. Only the last two change behaviour today; `push` is kept because
PR-Agent may handle push commands in a later configuration.
* Auto commands are `/describe` and `/review`. `/improve` stays available
on demand; the default auto list would add a second model call and a
second comment to every PR.
* Secrets live only in `/home/noel/self-hosted/pr-agent/.env` (mode 600) on
`server0`. The repository contains the compose file and an example env
file, never the token or webhook secret.
@@ -89,8 +92,10 @@ provider rejects the request before it reaches the model.
# Not verified
* The OpenCode Go API key was not present when this was committed, so no
model call and no real review have run. The first PR after the key is set
is the verification.
model call has completed. A dummy-key call now reaches the provider's
authentication check instead of failing on the missing session header,
so the remaining blocker is the credential. The first PR after the key is
set is the real verification.
* Whether `glm-5.3-flash` handles PR-Agent's structured review output well
enough. `glm-5.3` is configured as the fallback.
* Whether two gunicorn workers and the 1 GB memory limit hold under