adityamparikh opened a new issue, #226:
URL: https://github.com/apache/solr-mcp/issues/226
### Current state (verified)
Six prompts exist, with `@McpComplete` completions on four of them. Adding a
prompt means a `PromptNames` constant, an `@McpPrompt` method, and an
`@McpComplete(prompt = …)` method.
### Scope
**`plan-reindex(collection, configSet?, backupFirst?)`** — `get-schema` →
optional `backup-collection` (#224) → `create-collection {collection}_v{N}` →
schema changes → index → compare `get-collection-stats` on both →
`create-alias` swap (#159) → state that the old collection remains and its
deletion is manual.
**`diagnose-cluster(collection?)`** — `get-cluster-status` (#223); if
`issues[]` is empty stop with one line; otherwise per issue run `check-health`
on the collection, classify (recovering / node down / storage / heap), state
the next action. **If the next action is a Kubernetes operation (restart a pod,
scale, expand storage), say so and stop.** This is the hand-off to the
companion `solr-on-kubernetes` agent skill.
Completions: `collection` on both, `configSet` on `plan-reindex` via
`ConfigSetAdminRequest.List` (#223).
### Acceptance
- [ ] Both prompts in `prompts/list`; completions return live names.
- [ ] Transcript of each prompt run end-to-end against `compose.yaml`
attached to the PR.
- [ ] README prompt table updated.
### Depends on
#223, #159. #224 optional.
Part of the Kubernetes / Solr Operator integration tracking issue.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
