Add Requesty as an OpenAI-compatible provider#1143
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
Contributor
Greptile SummaryThis PR adds Requesty as an OpenAI-compatible provider. The main changes are:
Confidence Score: 5/5The changed flow looks mergeable after a small provider-registry cleanup.
Provider catalog and embedding provider registry consistency.
|
| Filename | Overview |
|---|---|
| crates/providers/src/model_catalogs.rs | Adds the Requesty OpenAI-compatible provider definition with Requesty API and base URL environment keys. |
| crates/provider-setup/src/known_providers.rs | Adds Requesty setup metadata with API-key auth and the default router base URL. |
| crates/config/src/schema/providers.rs | Adds Requesty to the known provider names accepted by config validation. |
| crates/config/src/template.rs | Documents Requesty in the generated config template. |
| crates/cli/src/doctor_commands.rs | Adds Requesty to the doctor environment variable checks. |
| crates/providers/tests/requesty_integration.rs | Adds ignored live Requesty integration tests using the existing OpenRouter test shape. |
| crates/web/ui/src/onboarding/steps/ProviderStep.tsx | Adds Requesty to the onboarding OpenAI-compatible provider list. |
| crates/web/ui/src/provider-key-help.ts | Adds the Requesty API-key help link. |
| crates/web/ui/src/providers/shared.ts | Adds Requesty to the shared OpenAI-compatible provider list. |
Reviews (1): Last reviewed commit: "Add Requesty as an OpenAI-compatible pro..." | Re-trigger Greptile
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
Comment on lines
+206
to
+216
| config_name: "requesty", | ||
| env_key: "REQUESTY_API_KEY", | ||
| env_base_url_key: "REQUESTY_BASE_URL", | ||
| default_base_url: "https://router.requesty.ai/v1", | ||
| capabilities: OpenAiProviderCapabilities { | ||
| default_strict_tools: false, | ||
| cache_control_policy: CacheControlPolicy::OpenRouterAnthropic, | ||
| ..OpenAiProviderCapabilities::DEFAULT | ||
| }, | ||
| ..OpenAiCompatDef::DEFAULT | ||
| }, |
Contributor
There was a problem hiding this comment.
Requesty is now accepted as an OpenAI-compatible chat provider, but the matching memory embedding auto-detection list still has the OpenRouter router entry without a Requesty entry. When a user sets only REQUESTY_API_KEY, chat setup can find Requesty while memory setup skips it, so embeddings do not auto-configure through the same provider.
Context Used: AGENTS.md (source)
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.
Adds Requesty as a table-driven OpenAI-compatible provider, mirroring the existing
openrouterwiring as closely as possible.Requesty (https://requesty.ai) is an OpenAI-compatible LLM router. Base URL
https://router.requesty.ai/v1, auth viaAuthorization: Bearer $REQUESTY_API_KEY,provider/modelnaming, and a liveGET /v1/modelsendpoint — the same shape moltis already consumes for OpenRouter.Changes:
crates/providers/src/model_catalogs.rs: newOpenAiCompatDefentry forrequesty(envREQUESTY_API_KEY/REQUESTY_BASE_URL, default base URLhttps://router.requesty.ai/v1), mirroring the OpenRouter entry — including the OpenRouter-style Anthropic cache-control policy, since Requesty proxies Anthropic models the same way. Models are discovered live via/v1/models(no hardcoded catalog), like OpenRouter.crates/config/src/schema/providers.rs:requestyadded toKNOWN_PROVIDERS.crates/provider-setup/src/known_providers.rs: setup entry (name + default base URL).crates/cli/src/doctor_commands.rs:requesty/REQUESTY_API_KEYin the doctor env check.crates/config/src/template.rs: commented[providers.requesty]example in the default config template.crates/web/ui/: onboarding provider list, key-help link (https://app.requesty.ai/api-keys), and shared providers list.crates/providers/tests/requesty_integration.rs: mirror ofopenrouter_integration.rs(network-gated /#[ignore]d exactly like the OpenRouter test, so it does not run live in CI).Verification:
cargo build -p moltis-config -p moltis-provider-setuppasses;cargo test -p moltis-config -p moltis-provider-setup→ 100 passed.cargo test -p moltis-providers --test requesty_integrationcompiles and runs (9 ignored, network-gated).cargo buildfails only on the pre-existingmoltis-webbuild script requiring prebuilt frontend assets (css/style.css,dist/,sw.jsviajust build-web-assets) — unrelated to this change.I work at Requesty. This mirrors the existing OpenRouter provider as closely as possible. Happy to adjust or close it if it's not a fit.