docs(readme): prerequisites, cost, CI details, and surface sample excerpt#2
Open
jlynshue wants to merge 1 commit into
Open
docs(readme): prerequisites, cost, CI details, and surface sample excerpt#2jlynshue wants to merge 1 commit into
jlynshue wants to merge 1 commit into
Conversation
… excerpt Factual README clarity fixes, all derivable from the repo: - Quick Start: add Prerequisites (AWS account + Bedrock model access; default model us.anthropic.claude-sonnet-4-6 / us-east-1 from runner.py + .env.example) - Quick Start: add cost note — a full audit makes 4 Bedrock calls (one per framework in ALL_AUDITS), each capped at 4096 output tokens; link to Bedrock pricing rather than guess a dollar figure - Development: state exactly what CI runs (ruff + structural eval harness via manual provider, py3.11/3.12, 3 fixtures x 4 audits) per .github/workflows/ci.yml - Example Output: lift a 3-line excerpt of the existing sample above the <details> Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017zfynhEadteeMKwYFAq4V8
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Factual / honesty-only README clarity fixes. No fabricated screenshots, demo output, metrics, or claims — every addition is verified against the repo source.
Changes
Quick Start → Prerequisites — states an AWS account with Amazon Bedrock model access (Console → Bedrock → Model access) is required. Documents the exact default model and region verified from
leverage_os/runner.pyand.env.example:us.anthropic.claude-sonnet-4-6inus-east-1, plus the override paths (BEDROCK_MODEL_ID/AWS_REGION,--model/--region). Notes--no-ai/manualprovider needs no AWS account.Quick Start → Cost — a full audit makes 4 Bedrock calls (one per framework, verified:
cli.pyloopsALL_AUDITS= 4 entries, oneinvoke_modeleach), each capped at 4096 output tokens (fromrunner.py). Links to the official Bedrock pricing page instead of guessing a dollar figure.Development → CI line — states exactly what CI runs, verified from
.github/workflows/ci.yml:ruff check .+ the structural eval harness (python -m leverage_os.evals --provider manual) on Python 3.11/3.12, over the 3 fixture personas intests/fixtures/× 4 audits. The repo has no pytest suite, so the line deliberately does not claim a pytest count.Example Output — lifts a 3-line excerpt (Leverage Index + Biggest Leverage Leak) of the existing in-
<details>sample above the fold. The text is copied verbatim from the existing sample — nothing invented.Markdown verified to parse.
Not done (needs a human)
🤖 Generated with Claude Code
https://claude.ai/code/session_017zfynhEadteeMKwYFAq4V8