feat: autonomous LLM-driven lifting (rpg-lift crate)#67
Merged
Conversation
New `rpg-lift` crate provides fire-and-forget semantic lifting via cheap LLM APIs (Anthropic Haiku, OpenAI GPT-4o-mini). Matches Microsoft RPG-ZeroRepo's autonomous pipeline approach while reusing our existing rpg-encoder lifting utilities. - LlmProvider trait with Anthropic Messages API and OpenAI Chat Completions API implementations (blocking HTTP via ureq v3) - Full pipeline: auto-lift → LLM entity lifting → module aggregation → file synthesis → domain discovery → hierarchy construction - Cost estimation with --dry-run support - Crash recovery via per-batch graph saves - Terminal progress bars with running cost ticker - CLI `lift` subcommand behind default-enabled feature flag - Retry logic with exponential backoff (2 retries per batch) Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
rpg-liftcrate withLlmProvidertrait abstracting Anthropic (Haiku) and OpenAI (GPT-4o-mini) APIsliftsubcommand with--dry-runcost estimation,--provider/--modelselectionCloses #66
Test plan
cargo build --workspace— compilescargo clippy --workspace --all-targets -- -D warnings— zero warningscargo test --workspace— all 640+ tests passcargo build -p rpg-cli --no-default-features— builds without lift featurerpg-encoder lift --help— shows correct subcommand helprpg-encoder lift --dry-run— cost estimation on a real reporpg-encoder lift --provider anthropic— end-to-end with API key🤖 Generated with Claude Code