feat(hopper): model pool routing in cecli.hopper#577
Open
JessicaMulein wants to merge 4 commits into
Open
Conversation
Move fast/code/think hopper pool, prompt classification, escalation, and apply-route from host integration into cecli.hopper with optional preload resolver hooks. Add 65 unit tests under cecli/tests/hopper/. Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Run verify-cecli-pre-commit on pr/hopper before upstream merge. Co-authored-by: Cursor <cursoragent@cursor.com>
Expand architect(?:ure|ural)? to explicit words so codespell does not flag "ure". Co-authored-by: Cursor <cursoragent@cursor.com>
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
cecli/hopper/— model pool (fast/code/think tiers), prompt classification, escalation, andapply_route_to_coderfor per-turn LiteLLM kwargs.set_backend_client_resolver,set_static_vram_bytes_resolverfor preload without coupling to a specific host runtime.CECLI_LLM_ENV, XDGlocal-llm/env,CECLI_REPO_ROOT/local-llm.env, or cwdlocal-llm.env.cecli/tests/hopper/.Motivation
Headless IDE hosts already use a three-tier model hopper for local LLM routing. Lifting the pure Python router into cecli keeps the engine product-neutral and testable without HTTP or desktop shell dependencies.
Test plan
python -m pytest cecli/tests/hopper/ -q(65 passed)