edit_prediction: Support self-hosted Sweep Next Edit models

[avoidthekitchen]

This adds support for running self-hosted Sweep Next Edit edit prediction models through Zed's OpenAI-compatible provider. The target use case is a local deployment based on sweepai/sweep-next-edit-1.5B, using the rewrite-window prompting approach described in OSS Next Edit. Personal user testing shows impressive quality from this small edit prediction model.

This is valuable because it allows more flexibility for Zed users to self-host state of the art next edit prediction models!

This PR addresses the self-hosted workflow discussed in #50929.
Note that the self-hosted model path needed more than just a new dropdown value. Zed has to build the rewrite-window prompt shape the model expects, map the rewritten window back into anchored edits, and make prompt_format: "infer" work with the filename-style model identifiers that llama-server local server reports.

The main changes are:

• add a Sweep prompt format for OpenAI-compatible edit prediction providers and route it to a dedicated SweepPrompt model path
• build Sweep rewrite-window prompts from the active cursor window, recent change history, and related file excerpts
• convert rewrite responses back into anchored edits and suppress no-op rewrites
• add fixed cursor-window extraction used by the Sweep rewrite prompt path
• recognize sweep-next-edit model names during infer, including filename-style identifiers such as sweepai_sweep-next-edit-1.5B_sweep-next-edit-1.5b.q8_0.v2.gguf
• reject reserved Sweep prompt tokens before sending malformed requests to a self-hosted server
• update the docs to describe the actual Sweep rewrite-window prompt format

Local setup used for manual verification:

llama-server \
  --hf-repo sweepai/sweep-next-edit-1.5B \
  --hf-file sweep-next-edit-1.5b.q8_0.v2.gguf \
  --ctx-size 8192 \
  --host 127.0.0.1 \
  --port 8080

{
  "edit_predictions": {
    "provider": "open_ai_compatible_api",
    "open_ai_compatible_api": {
      "api_url": "http://127.0.0.1:8080/v1/completions",
      "model": "sweepai_sweep-next-edit-1.5B_sweep-next-edit-1.5b.q8_0.v2.gguf",
      "prompt_format": "infer",
      "max_output_tokens": 512
    }
  }
}

The request that produced this PR included screenshots of the OpenAI-compatible provider configuration and the prompt format dropdown with Sweep selected.

Tests added in this branch:

• test_sweep_prompt_format_routes_to_sweep_prompt_model
• test_fixed_line_window_around_cursor_start_middle_and_end
• test_sweep_prompt_request_prediction_diffs_rewritten_window_into_anchored_edits
• test_sweep_prompt_request_prediction_returns_none_for_identical_rewrite
• test_original_window_for_current_window_uses_latest_pre_edit_snapshot
• test_original_window_for_current_window_returns_none_without_matching_history
• test_recent_change_block_from_event_formats_original_and_updated_sections

Verification run locally:

• cargo test -p zed sweep_prompt_format_routes
• cargo test -p zed subscribe_uses_stale_provider_config
• cargo test -p edit_prediction sweep_prompt
• cargo test -p edit_prediction fixed_line_window_around_cursor_start_middle_and_end
• cargo test -p edit_prediction test_sweep_prompt_request_prediction_diffs_rewritten_window_into_anchored_edits
• cargo test -p edit_prediction test_sweep_prompt_request_prediction_returns_none_for_identical_rewrite
• ./script/clippy -p zed -p edit_prediction -p settings_content

Release Notes:

• Added support for self-hosted Sweep Next Edit models in OpenAI-compatible edit predictions, including the sweep prompt format and infer detection for sweep-next-edit model names.

[cla-bot]

Thank you for your pull request and welcome to our community. We could not parse the GitHub identity of the following contributors: mistercheese.
This is most likely caused by a git client misconfiguration; please make sure to:

1. check if your git client is configured with an email to sign commits git config --list | grep email
2. If not, set it up using git config --global user.email email@example.com
3. Make sure that the git commit email is configured in your GitHub account settings, see https://github.com/settings/emails

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 497eccb7c0

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.

[chatgpt-codex-connector]

You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard.
To continue using code reviews, you can upgrade your account or add credits to your account and enable them for code reviews in your settings.

[DarkGhostHunter]

Weird, since I can use Sweep Next Edit 1.5B using the qwen parser without problems.

[iavael]

@DarkGhostHunter you just use FIM completion instead of Next Edit Suggestion, which is more complex and requires model-specific format handling in code

You can read more about Sweep format here
https://huggingface.co/sweepai/sweep-next-edit-v2-7B

[DarkGhostHunter]

Got it. One thing is Autocomplete at caret position, the other is Next Edit beyond the caret.

[probably-neb]

Thanks for this, and sorry for the delay in merging.

[avoidthekitchen]

Thanks a ton, I'm looking forward to this!

[sargunv]

amazing, excited to try it out in Zed!

[reneleonhardt]

Amazing contribution! 🚀

I guess https://huggingface.co/Chris-Kode/sweep-next-edit-1.5b-mlx doesn't work in the Ollama settings.

What is the fastest compatible MLX inference runtime on macOS?
https://github.com/youssofal/MTPLX

[DarkGhostHunter]

Amazing contribution! 🚀

I guess https://huggingface.co/Chris-Kode/sweep-next-edit-1.5b-mlx doesn't work in the Ollama settings.

What is the fastest compatible MLX inference runtime on macOS? https://github.com/youssofal/MTPLX

AFAIK, Ollama support for MLX is still rolling out. Try LM Studio, MLC-LLM and vLLM.