Add Claude Code CLI as an LLM provider#64
Open
Builder106 wants to merge 1 commit into
Open
Conversation
Support LLM_PROVIDER=claude_code so scoring/tailoring can run through the Claude Code CLI without an API key. Detects the claude binary in tier checks, adds a claude_code branch to the init wizard, and wires the provider into the LLM dispatch path.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Adds
LLM_PROVIDER=claude_codeso the scoring and tailoring stages can run through the local Claude Code CLI, with no API key required.Why
ApplyPilot already requires the Claude Code CLI for the Tier 3 auto-apply stage. This lets users who have the CLI installed reuse it as the LLM backend for Tier 2 (scoring/tailoring) too, instead of also provisioning a Gemini/OpenAI key or a local model server.
Changes
llm.py: aclaude_codebackend onLLMClientthat converts the OpenAI-style message list into a single prompt and shells out to theclaudeCLI. Selected whenLLM_PROVIDER=claude_code.config.py: tier detection treatsLLM_PROVIDER=claude_code+ aclaudebinary on PATH as a satisfied LLM backend (Tier 2), and the missing-backend hint mentions the option.wizard/init.py: the init wizard offersclaude_codeas a provider choice and writes the env lines.Notes
claudebinary already documented for Tier 3.claudeisn't on PATH, the existing API-key/local-URL providers are unaffected.