Conversation
Add a FutureInfra ProviderSpec on the generic openai_compat gateway path, the matching ProviderConfig block, and tests pinning the wiring. Mirrors the Opper provider (HKUDS#242). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This branch has not been deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Adds FutureInfra as a named OpenAI-compatible gateway. FutureInfra (https://futureinfra.ai/) is a Korean cloud provider whose AI router exposes an OpenAI-compatible API at
https://futureinfra.ai/v1/ai(POST /chat/completions,GET /models). One key reaches 300+ models from several vendors, withprovider/modelids such asopenai/gpt-4o-mini,anthropic/claude-sonnet-4anddeepseek/deepseek-chat.Mirrors the Opper provider added in #242: a
ProviderSpecon the genericopenai_compatgateway path, the matchingProviderConfigblock, and tests pinning the wiring.Related Issues
None.
Changes Made
core/providers/registry.py: newfutureinfraProviderSpec(inserted afteropper),endpoint_class="gateway",env_key="FUTUREINFRA_API_KEY",detect_by_base_keyword="futureinfra.ai",default_api_base="https://futureinfra.ai/v1/ai".core/config.py:futureinfrablock inProvidersConfig.tests/test_futureinfra_provider.py: pins registration, config block, gateway wiring, base URL / env var, endpoint class of the default base, empty key-prefix heuristic, andstrip_model_prefix=False.Two provider-specific choices, both covered by tests:
strip_model_prefixstays off: FutureInfra ids areprovider/modelslugs, so the prefix is part of the id.supports_prompt_cachingis left at the default (False); this PR only relies on the standard chat completions API (streaming and tool calling).Checklist
Additional Notes
Tests run locally (Python 3.12, deps from
scripts/ci/requirements.lock, Windows):pre-commit run --files core/config.py core/providers/registry.py tests/test_futureinfra_provider.py(actionlint skipped, no workflow changes): all passedpytest tests/test_futureinfra_provider.py tests/test_opper_provider.py tests/test_requesty_provider.py tests/test_forge_provider.py tests/test_provider_egress.py tests/test_bedrock_provider.py tests/test_provider_cli.py tests/test_provider_credentials.py tests/test_provider_protocols.py tests/test_config_layering.py tests/test_config_layers.py: 139 passedLive call test not attached (no API key used).
Disclosure: this PR is submitted on behalf of FutureInfra, and the change was drafted with Claude Code. Happy to adjust anything to match project conventions, or to close it if a named provider is not wanted.
🤖 Generated with Claude Code