feat: add OrcaRouter as an LLM Advisor provider - #8826
Merged
nvuillam merged 3 commits intoAug 31, 2026
Conversation
Add OrcaRouter as a first-class LLM provider for the LLM Advisor, mirroring the Grok provider integration: it is an OpenAI-compatible AI gateway, so it reuses langchain_openai ChatOpenAI against https://api.orcarouter.ai/v1. Users enable it with LLM_PROVIDER: orcarouter and ORCAROUTER_API_KEY.
zsanig22-dotcom
requested review from
Kurt-von-Laven,
bdovaz,
echoix and
nvuillam
as code owners
August 29, 2026 07:58
SPELL_CSPELL reported 25 unknown words, all occurrences of the new provider name in code, docs and the CHANGELOG. Added "ORCAROUTER" and "orcarouter" to the .cspell.json words list, next to the existing DEEPSEEK/deepseek and OLLAMA/Ollama/ollama entries of the other providers. The CamelCase OrcaRouterProvider was already accepted, as cspell splits it into known words. The merge of main in the previous commit fixes test-doc-gen, which failed on a langchain_core==1.5.6 pin incompatible with langchain_google_genai 4.3.5 (needs >=1.6.0). That conflict is unrelated to this PR and was fixed on main by oxsecurity#8838.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add OrcaRouter as a first-class LLM Advisor provider, mirroring the existing Grok integration. OrcaRouter is an OpenAI-compatible AI gateway built for both models and agents: like OpenRouter it exposes a provider/model namespace across many models, while adding adaptive routing, automatic failover, zero-markup inference, observability, guardrails, and agent-tool governance behind the same endpoint. Adding it as a named provider means MegaLinter users can use that stack directly instead of treating OrcaRouter as an anonymous custom base URL. It also runs gateway-level, zero-trust security for AI agents on the same endpoint — screening every prompt/response and governing every tool call on a default-deny basis, with no application code changes.
Changes: new
llm_provider_orcarouter.py(ChatOpenAI againsthttps://api.orcarouter.ai/v1, default modelorcarouter/fusion-mini), factory + lazy module registration,ORCAROUTER_API_KEY, provider doc page, and provider tables indocs/llm-advisor.md,docs/llm-providers.mdandmkdocs.yml.Verification: ruff (repo config) and black pass; existing
test_llm_advisor_integration.pypasses (15 tests + 3 subtests); live-tested the provider throughLLMProviderFactoryagainstapi.orcarouter.aiwith a real key (model response, HTTP 200).I'm an engineer on the OrcaRouter team. Discord: discord.gg/YEubt8enRA · X: https://x.com/OrcaRouter