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 in this releaseavailable in distributionsupported
  • Providerollama
  • Profilelocal-private
  • Destinationhttp://127.0.0.1:11434/api (local)
  • Modelqwen3.5:4b
  • Credentialnone
  • Workflowinference.backend: local-ollama · reusable workflow yes

Default installed workflow path: inference.backend: local-ollama in .reviewsensei.yml, with the packaged local model unless inference.model names another one.

  • 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 in this releaseavailable in distributionsupported
  • Providerollama
  • Profiledeep-verification
  • Destinationhttps://ollama.com/api (remote)
  • Modeldeepseek-v4.1-flash:cloud
  • CredentialOLLAMA_API_KEY
  • Workflowinference.backend: cloud-ollama · reusable workflow yes

Installed workflows opt in with inference.backend: cloud-ollama in .reviewsensei.yml and the 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 in this releaseavailable 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

implemented in this releaseavailable in distributionsupportedexperimental
  • Provideropenrouter
  • Profileopenrouter-sonnet / openrouter-gpt (CLI profiles)
  • Destinationhttps://openrouter.ai/api/v1 (remote)
  • Modeldeepseek/deepseek-v4.1-flash
  • CredentialOPENROUTER_API_KEY
  • Workflowinference.backend: openrouter · reusable workflow yes

Installed workflows opt in with inference.backend: openrouter in .reviewsensei.yml and the repository OPENROUTER_API_KEY secret. The supported label applies to this hosted workflow path with allowlisted models only.

  • CLIyes
  • evaluateyes
  • npx launcheryes
Evidence
src/review_sensei/providers/registry.pysrc/review_sensei/providers/openrouter.pysrc/review_sensei/providers/profiles.pysrc/review_sensei/provider_config.pypackages/npm/cli/README.mdtests/test_cli.pydocs/installation.mddocs/data-handling.mddocs/adr/0045-openrouter-trusted-configuration.md
  • Hosted OpenRouter accepts only the published allowlist in provider_config.HOSTED_OPENROUTER_DEFAULTS; the default model deepseek/deepseek-v4.1-flash is pinned to Morph with no fallback, data collection denied, and ZDR required.
  • CLI profiles openrouter-sonnet and openrouter-gpt remain unqualified and require --allow-unqualified-profile for live review; tests/test_cli.py covers the opt-in and fail-closed paths.
  • The npx launcher forwards argv to the Python CLI; reaching OpenRouter still requires explicit --provider openrouter (or --profile) plus OPENROUTER_API_KEY.
  • Hosted workflows reject allow_unqualified_profile=true; use the CLI for unqualified profile runs.

Released docs: v0.6.19 · source 2869116d4205 · build provenance