feat(providers): add openai-compatible embeddings support

[badgerbees]

📝 Description

Add OpenAI-compatible embeddings support to the provider layer so vLLM-style endpoints can serve embeddings without forwarding dimensions upstream. The new provider path sends model and input, truncates vectors locally when a smaller width is requested, and preserves existing extra_body settings except for dimensions.

🗣️ Type of Change

• 🐞 Bug fix (non-breaking change which fixes an issue)
• ✨ New feature (non-breaking change which adds functionality)
• 📖 Documentation update
• ⚡ Code refactoring (no functional changes, no api changes)

🤖 AI Code Generation

• 🤖 Fully AI-generated (100% AI, 0% Human)
• 🛠️ Mostly AI-generated (AI draft, Human verified/modified)
• 👨‍💻 Mostly Human-written (Human lead, AI assisted or none)

🔗 Related Issue

N/A

📚 Technical Context (Skip for Docs)

• Reference URL: N/A
• Reasoning: The provider stack already handled chat and streaming for OpenAI-compatible backends, but it had no embeddings seam. This change adds EmbeddingProvider, wires it through the HTTP provider facade, and implements /embeddings calls in the shared OpenAI-compatible client.

🧪 Test Environment

• Hardware: PC
• OS: Windows
• Model/Provider: OpenAI-compatible provider tests (httptest)
• Channels: N/A

📸 Evidence (Optional)

Click to view Logs/Screenshots

Validation passed:

• go test ./pkg/providers/...

☑️ Checklist

• My code/docs follow the style of this project.
• I have performed a self-review of my own changes.
• I have updated the documentation accordingly.

[CLAassistant]

All committers have signed the CLA.

[Copilot]

Pull request overview

Adds OpenAI-compatible embeddings support to the provider layer, enabling OpenAI-compat backends (e.g., vLLM-style endpoints) to serve embeddings without forwarding dimensions upstream, while still allowing callers to request a smaller output width via local truncation.

Changes:

• Introduces a new EmbeddingProvider interface in pkg/providers.
• Implements /embeddings calls (query + batch) in openai_compat.Provider, omitting dimensions from the upstream request and truncating vectors client-side when requested.
• Wires embedding methods through the httpapi HTTP provider facade and adds httptest coverage for the new behavior.

Reviewed changes

Copilot reviewed 5 out of 5 changed files in this pull request and generated 1 comment.

Show a summary per file

File	Description
pkg/providers/types.go	Adds EmbeddingProvider interface for embeddings query/batch.
pkg/providers/openai_compat/embeddings.go	Implements embeddings request/response handling and local truncation helper.
pkg/providers/openai_compat/embeddings_test.go	Adds tests for omitting upstream dimensions and truncation/error behavior.
pkg/providers/httpapi_facade.go	Adds compile-time assertion that HTTPProvider satisfies EmbeddingProvider.
pkg/providers/httpapi/http_provider.go	Delegates EmbedQuery/EmbedBatch to the OpenAI-compat provider implementation.

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[github-actions]

This PR has had no activity for 7 days and has been marked as stale. If you are still working on it, please push an update or leave a comment; otherwise it will be closed automatically in 7 days.

[github-actions]

This PR has been closed after 14 days of inactivity. If you would like to continue, feel free to reopen it or submit a new PR.