Repository navigation
feat(llm): add speed option for provider fast mode - #8
Merged
Merged
Conversation
Co-Authored-By: Leonardo Marciano <leonardo.marciano@toolzz.me>
Contributor
Author
|
I'll fix CI failures and address comments from users with write access. I'll skip comments containing "(aside)".
|
Co-Authored-By: Leonardo Marciano <leonardo.marciano@toolzz.me>
Co-Authored-By: Leonardo Marciano <leonardo.marciano@toolzz.me>
Owner
|
Lgfm |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What and why
Adds
speed=next tothinking=to run the editing LLM in the provider's fast mode: same model, faster output, about 2x the price.Session,wsp.read/fix/write/improveand the backends takespeed(None= standard,True/"fast","standard", or a tier like"ultrafast"). CLI:--speed/--fast. Saved inresult.json.speed; OpenAI and Open Responses sendservice_tier.thinking.type="disabled", sothinking=Falsenow falls back toeffort="low"(plus the act-directly prompt) on such models.usage.thinking_tokensis recorded so you can see how much it still thought.experiments/exp8/run_edit.pytakes--speed fast. Docs, README,llms.txtand the changelog are updated.How it was tested
ruff check . && ruff format --check .pytest(27 passed; new tests for speed on both providers, onSession/Result, and the low-effort fallback)CHANGELOG.mdentry (if user-facing)mypy src/weightspacespeed="fast", thinking=False: edited a numpy vector correctly, response reportedspeed='fast', 0 thinking tokens.