docs: fix factual errors in LLM provider references#27
Merged
timeleft-- merged 1 commit intomainfrom Mar 10, 2026
Merged
Conversation
- Fix any-llm-sdk GitHub URL: mozilla-ai/any-llm (correct) instead of marekstephens/any-llm-sdk (non-existent) - Update OpenRouter model count: 300–500+ from 60+ providers (was understated at 100+) - Remove unsourced CPU latency claim (~200–500ms) for LLMLingua-2 compression - Consolidate messaging: OpenRouter as default provider, any-llm-sdk enables future multi-provider support Fixes based on: - any-llm-sdk PyPI package maintained by Mozilla AI at mozilla-ai/any-llm - OpenRouter current provider count verified at openrouter.ai - LLMLingua-2 paper (2403.12968) only benchmarks on GPU; no published CPU latency data Co-Authored-By: Claude Haiku 4.5 <noreply@anthropic.com>
timeleft--
added a commit
that referenced
this pull request
Mar 10, 2026
…ules Complete the corrections started in PR #27. That PR fixed README.md and AGENTS_SETUP_INSTRUCTIONS.md but missed the same errors in protocol READMEs, Python docstrings, the FAQ, and the protocols __init__.py. Corrections applied across 8 files: ACE naming: "Agentic Context Engine" → "Agentic Context Engineering" - README.md, protocols/__init__.py, ace/README.md, ace/__init__.py, docs/fava_trails_faq.md ACE affiliations: "Stanford/SambaNova" → "Stanford, UC Berkeley, and SambaNova" - README.md, AGENTS_SETUP_INSTRUCTIONS.md, ace/README.md, ace/__init__.py, docs/fava_trails_faq.md SECOM affiliations: "Microsoft" → "Tsinghua University and Microsoft" - README.md, secom/README.md, secom/__init__.py, docs/fava_trails_faq.md "Zero hallucination" → "Purely extractive" (papers don't make that claim) - README.md, secom/README.md, docs/fava_trails_faq.md OpenRouter "100+" → "300–500+" (missed occurrence in AGENTS_SETUP_INSTRUCTIONS.md) Removed link to kayba-ai/agentic-context-engine (community reimplementation that renames core ACE concepts; official repo is ace-agent/ace) Fixed protocols/__init__.py docstring claiming protocols are not designed to run simultaneously — they ARE composable (staggered order values: ace=10, rlm=15, secom=20) All 558 tests pass. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
7 tasks
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
Corrects three factual errors in documentation regarding LLM provider configuration:
marekstephens/any-llm-sdk. Corrected tomozilla-ai/any-llm(the official PyPI package maintainer).Files changed
README.md— 2 occurrences of any-llm-sdk URL + OpenRouter countAGENTS_SETUP_INSTRUCTIONS.md— 1 occurrence of any-llm-sdk URLAll corrections consolidate messaging: OpenRouter as the default provider, any-llm-sdk infrastructure enables multi-provider support in future versions.
Verification
🤖 Generated with Claude Code