ReviewSensei.dev
Provider matrix

Release-aware provider support

Conservative labels derived from the shipped registry, named profiles, and installed workflow contract. Planned adapters stay explicitly not implemented.

Ollama (local)

implemented on mainavailable in distributionsupported
  • Providerollama
  • Profilelocal-private
  • Destinationhttp://127.0.0.1:11434/api (local)
  • Modelqwen3.5:4b
  • Credentialnone
  • Workflowlocal · reusable workflow yes

Default installed workflow path via REVIEWSENSEI_PROVIDER_MODE=local and local model variables.

  • CLIyes
  • evaluateyes
  • npx launcheryes
Evidence
src/review_sensei/providers/registry.pysrc/review_sensei/providers/profiles.pydocs/installation.md
  • Requires a reachable local Ollama runner on loopback.
  • No bearer credential is used for the default local-private profile.

Ollama Cloud

implemented on mainavailable in distributionsupported
  • Providerollama
  • Profiledeep-verification
  • Destinationhttps://ollama.com/api (remote)
  • Modeldeepseek-v4.1-flash:cloud
  • CredentialOLLAMA_API_KEY
  • Workflowcloud · reusable workflow yes

Installed workflows opt in with REVIEWSENSEI_PROVIDER_MODE=cloud and repository OLLAMA_API_KEY secret.

  • CLIyes
  • evaluateyes
  • npx launcheryes
Evidence
src/review_sensei/providers/registry.pysrc/review_sensei/providers/profiles.pydocs/installation.mddocs/data-handling.md
  • Requires a provisioned Ollama Cloud account and OLLAMA_API_KEY.
  • Cloud egress is explicit opt-in; local runs cannot silently fail over to Ollama Cloud.

OpenAI-compatible (Python boundary)

implemented on mainavailable in distribution
  • Provideropenai-compatible
  • Profilefast-triage
  • Destinationhttps://api.openai.com/v1 (remote)
  • Modelgpt-4o-mini
  • CredentialOPENAI_API_KEY
  • Workflownot applicable · reusable workflow no

Installed GitHub workflows do not pass --profile; fast-triage is an explicit CLI/evaluate path only.

  • CLIyes
  • evaluateyes
  • npx launcheryes
Evidence
src/review_sensei/providers/registry.pysrc/review_sensei/providers/openai_compatible.pydocs/public-contracts.mddocs/adr/0041-production-provider-adapters-and-per-stage-profiles.md
  • Named profiles are immutable presets; custom endpoints require unprofiled openai-compatible use.
  • Not enabled by the reusable workflow; requires OPENAI_API_KEY and --profile fast-triage or equivalent settings.
  • The npx launcher forwards argv to the Python CLI; reaching openai-compatible still requires explicit --profile fast-triage (or unprofiled flags) plus OPENAI_API_KEY.

OpenRouter

plannedsource onlynot implementedexperimental
  • Provideropenrouter
  • Profilenone
  • Destinationhttps://openrouter.ai/api/v1 (remote)
  • Modelnot fixed
  • CredentialOPENROUTER_API_KEY
  • Workflownot applicable · reusable workflow no

Adapter source exists on main, but no named profile, CLI flags, or reusable-workflow path expose OpenRouter yet.

  • CLIno
  • evaluateno
  • npx launcherno
Evidence
src/review_sensei/providers/registry.pysrc/review_sensei/providers/openrouter.py
  • Registry registers openrouter, but engine surfaces remain disabled until routing policy and operator docs ship.
  • No named profile or workflow provider mode selects OpenRouter in installed callers.