[Bug]: Changing an LLM provider's context breaks its LLM proxies (404) until each proxy is redeployed
Maintainers usually reply within 1 day
Nobody has claimed this yet.
Assessment
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Newbie friendliness
- 57/100
Research direction
Start with gateway/gateway-controller/pkg/utils/llm_transformer.go near line 209, where the provider context is copied into a proxy's loopback upstream, and trace how provider deployments update routes. Reproduce the issue using the listed provider and proxy API steps, then check whether the proxy route refreshes after the provider context changes. Done means the proxy keeps returning 200 after only the provider is redeployed, or the AI Workspace clearly identifies affected proxies that need redeployment.
Written by the indexing model from the issue text.
Description
Please select the area the issue is related to
Gateway, AI Workspace
Please select the aspect the issue is related to
Aspect/AI (AI/LLM integration, MCP, AI readiness)
Description
When an LLM provider's context changes and the provider is deployed again, every LLM proxy that uses it starts returning 404. platform-api still shows those proxies as DEPLOYED, and they keep failing until each one is deployed again.
When the gateway builds a proxy's route, it copies the provider's context into the proxy's loopback upstream (gateway/gateway-controller/pkg/utils/llm_transformer.go:209). Deploying the provider updates only the provider, so the proxy keeps forwarding to the old context. The router log shows the proxy's request going to the old path:
"POST /b07proxy/chat/completions HTTP/1.1" /b07prov/chat/completions - 404 - direct_response ...
The AI Workspace warning shown when a provider's context is edited ("You have modified the context of this service provider. After updating, you will need to redeploy on the gateway for the changes to take effect.") mentions only the provider, not its proxies.
Expected: proxies keep working after their provider's context changes, or the user is told which proxies need to be deployed again.
Actual: the proxies return 404 while showing DEPLOYED.
Related: #3493.
Steps to Reproduce
- Create a provider:
POST /api/v0.9/llm-providerswith{"id":"b07-prov","displayName":"b07-prov","version":"v1.0","template":"openai","context":"/b07prov","upstream":{"main":{"url":"<echo-backend>/v1"}},"accessControl":{"mode":"allow_all"}}. - Create a proxy on it:
POST /api/v0.9/llm-proxieswith{"id":"b07-proxy","displayName":"b07-proxy","version":"v1.0","projectId":"default","context":"/b07proxy","provider":{"id":"b07-prov"}}. - Deploy the provider, then the proxy, to the same gateway (
POST .../deployments,base: current). Wait forDEPLOYEDon both. - Call the proxy:
POST <router>/b07proxy/chat/completionswith{"model":"gpt-4o","messages":[{"role":"user","content":"hi"}]}. It returns200. - Change the provider's context:
GET /api/v0.9/llm-providers/b07-prov, set"context":"/b07prov-new", andPUTit back. It returns200. - Deploy only the provider again. Wait for
DEPLOYED. - Call the provider at its new context:
POST <router>/b07prov-new/chat/completions. It returns200. - Call the proxy again (same request as step 4). It returns
404({"error":"Not Found"}), and still does 20 seconds later.GET /api/v0.9/llm-proxies/b07-proxy/deploymentsstill shows the proxyDEPLOYED. - Deploy the proxy again. The same call now returns
200.
Severity Level of the Issue
Severity/Major (Important functionality is broken. Should be prioritized. Doesn't need immediate attention)
Environment Details (with versions)
- Source:
mainatf5c93849. - platform-api built from source (SQLite).
- Gateway images (
gateway-controller/gateway-runtime2026.09.24) built from that commit. - Echo backend:
ghcr.io/wso2/api-platform/sample-service:latest. - macOS with Rancher Desktop.
- Dominant language
- Go
- Stars
- 85
- Forks
- 137
- Avg merge
- 1d 12h
- Merged PRs (30d)
- 247
Getting set up
- No Dockerfile or Docker Compose file
- Has a pull request template
- No contributing guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
More from wso2/api-platform
-
Area/DeveloperPortal Aspect/UI Severity/Minor Type/Bug
Difficulty 1/5 Under an hour Newbie friendliness 88/100
wso2/api-platform#4369 ·
Maintainers usually reply within 1 day
-
[Bug]: host-rewrite policy documentation lists fewer allowed host characters than the policy acceptsOpenArea/Policies Aspect/Other Severity/Trivial Type/Bug
Difficulty 1/5 Under an hour Newbie friendliness 91/100
wso2/api-platform#4355 ·
Maintainers usually reply within 1 day
-
Area/Gateway Aspect/API Severity/Minor Type/Bug
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
wso2/api-platform#4348 ·
Maintainers usually reply within 1 day
-
Aspect/AI Aspect/API. Severity/Major
Difficulty 2/5 1-3 hours Newbie friendliness 77/100
wso2/api-platform#4343 ·
Maintainers usually reply within 1 day
-
Area/Policies Aspect/Configuration Severity/Minor Type/Bug
Difficulty 2/5 1-3 hours Newbie friendliness 74/100
wso2/api-platform#4330 ·
Maintainers usually reply within 1 day
All issues in wso2/api-platform
Similar issues
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
Maintainers usually reply within 1 day
-
Inconsistency between golang and cue in specPossibly taken A pull request linked to this issue is open or already merged. Open
Difficulty 1/5 Under an hour Newbie friendliness 88/100
Maintainers usually reply within 1 day
-
security
Difficulty 2/5 1-3 hours Newbie friendliness 68/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 73/100
Tencent/LoopForge#1087 · 1 comment ·
Maintainers usually reply within 1 day