Repository navigation
[FEATURE] pre_chat.messages.transform hook for image-to-text stripping #25494
Description
Verification
- I have verified this feature request has not been suggested before (see Proposal: message.parts.before plugin hook for multimodal preflight #24125, system.transform fires after messages.transform — plugins can't coordinate system+message mutations #19960 — this issue proposes a unified approach combining their ideas)
Problem
Plugins cannot strip or transform messages before they reach the LLM. When a user attaches an image, the LLM errors out with "this model does not support image input".
The existing hooks have limitations:
experimental.chat.messages.transformhasinput: {}— it never receives messages (system.transform fires after messages.transform — plugins can't coordinate system+message mutations #19960)- Proposal: message.parts.before plugin hook for multimodal preflight #24125 proposes
message.parts.beforefor image handling but it is not implemented - No hook fires BEFORE the LLM is called
Proposed Solution
Add pre_chat.messages.transform — a hook that fires before the LLM, receiving the full messages array and allowing plugins to transform them:
"pre_chat.messages.transform"?: (
input: {
sessionID: string
agent: string
model: Model
messages: { info: Message; parts: Part[] }[]
},
output: { messages: { info: Message; parts: Part[] }[] },
) => Promise<void>Use Cases
- Image-to-text stripping: Scan for
FilePartwithimage: true, call a Vision server (Qwen2.5-VL-3B), replace withTextPartcontaining the description - Vision plugin integration: Transform messages on-the-fly so the LLM always receives text-only input
- Pre-inference modification: Any plugin that needs to modify messages before the LLM
Backward Compatibility
experimental.chat.messages.transformis non-functional (empty input). Marked@deprecatedand replaced by this new hook- No breaking changes to existing hooks
Required Go Binary Change (separate PR)
The Go binary needs to:
- Register
pre_chat.messages.transformhooks from the plugin registry - Call them with the messages array before invoking the LLM
- Collect
output.messagesand pass the transformed array to the model
PR
SDK type changes: #25493
Metadata
Metadata
Assignees
Labels
No labels
Activity
github-actions commentedon May 2, 2026
This issue doesn't fully meet our contributing guidelines.
What needs to be fixed:
[FEATURE]:(current title: "feat(plugin): add pre_chat.messages.transform hook for image stripping")Please edit this issue to address the above within 2 hours, or it will be automatically closed.
This issue might be a duplicate of existing issues. Please check:
experimental.chat.messages.transformnot receiving messages/context, which is the same root problem described hereIf you believe this was flagged incorrectly, please let a maintainer know.
[-]feat(plugin): add pre_chat.messages.transform hook for image stripping[/-][+][FEATURE] pre_chat.messages.transform hook for image-to-text stripping[/+]github-actions commentedon May 2, 2026
Thanks for updating the issue! Everything looks good now — the title, verification checkbox, and description all meet our contributing guidelines.
github-actions commentedon Jul 3, 2026
To stay organized issues are automatically closed after 60 days of no activity. If the issue is still relevant please open a new one.