Add Groq platform (provider 4)

The 7th registry row and the first pure-pattern cycle: id "groq", GROQ_API_KEY > auth.json "groq" scope, https://api.groq.com/openai/v1 with KIGI_GROQ_BASE_URL override, OpenAI listing + ChatCompletions + Passthrough dialect (Groq accepts the OpenAI-style reasoning_effort scalar verbatim), enrichment-backed metadata with the tool-calling restriction (the listing carries whisper/tts/guard noise — 8 of 15 enrichment entries are non-chat). Review verdict: faithful pattern repeat, zero blocking findings — row facts verified against live Groq docs, registry integrity at 7, e2e proven strong on both axes (restriction + dialect mapping). Added the recommended pin: managed keys split on the FIRST slash, so Groq's provider-native slashed ids (openai/gpt-oss-120b and 10 more) round-trip as groq/openai/gpt-oss-120b → (Groq, openai/gpt-oss-120b). Also fixes a pre-existing test race this cycle surfaced: the enterprise- endpoints test asserted moonshot's fixed base while non-serial, racing serial tests that legitimately point KIGI_MOONSHOT_CN_BASE_URL at wiremock; now serial + env-unset like its documented siblings. Two display-only advisories logged as tracked debt (Groq's delta.reasoning field invisible in the TUI; platform-generic rate-limit copy).
2026-07-21 08:08:43 -04:00
parent 7efb4b07cc
commit 49e6414c29
5 changed files with 146 additions and 9 deletions
@@ -594,7 +594,8 @@ mod tests {
                MOONSHOT_AI_METHOD_ID,
                "openai",
                "anthropic",
-                "deepseek"
+                "deepseek",
+                "groq"
            ]
        );
        assert_eq!(default_id(&built), Some(XAI_API_KEY_METHOD_ID));
@@ -623,7 +624,8 @@ mod tests {
                MOONSHOT_AI_METHOD_ID,
                "openai",
                "anthropic",
-                "deepseek"
+                "deepseek",
+                "groq"
            ]
        );
        assert_eq!(default_id(&built), Some(CACHED_TOKEN_AUTH_METHOD_ID));
@@ -645,7 +647,8 @@ mod tests {
                MOONSHOT_AI_METHOD_ID,
                "openai",
                "anthropic",
-                "deepseek"
+                "deepseek",
+                "groq"
            ]
        );
        assert_eq!(default_id(&built), Some(CACHED_TOKEN_AUTH_METHOD_ID));
@@ -670,7 +673,8 @@ mod tests {
                MOONSHOT_AI_METHOD_ID,
                "openai",
                "anthropic",
-                "deepseek"
+                "deepseek",
+                "groq"
            ]
        );
        assert_eq!(default_id(&built), None);
@@ -6638,7 +6638,12 @@ reasoning_effort = "low"
        );
    }
    #[test]
+    #[serial]
    fn e2e_enterprise_endpoints_only_no_model_override() {
+        // Hermetic: the moonshot-base assertion below races serial tests
+        // that legitimately point KIGI_MOONSHOT_CN_BASE_URL at wiremock —
+        // this test was non-serial and read the env mid-guard.
+        let _cn = EnvGuard::unset(kigi_models::MOONSHOT_CN_BASE_URL_ENV);
        let (_, models) = resolve_models_from_toml(
            r#"
            [endpoints]
@@ -1123,6 +1123,89 @@ mod tests {
        assert_eq!(cfg.chat_compat, kigi_sampling_types::ChatCompat::Kimi);
    }

+    /// Groq-cycle e2e: pure pattern — polluted listing restricted to
+    /// tool-calling enrichment models, Passthrough dialect (OpenAI-style
+    /// reasoning_effort untouched on this wire).
+    #[tokio::test(flavor = "multi_thread")]
+    #[serial_test::serial]
+    async fn groq_listing_restricts_and_maps_passthrough_dialect() {
+        let platform_server = wiremock::MockServer::start().await;
+        wiremock::Mock::given(wiremock::matchers::method("GET"))
+            .and(wiremock::matchers::path("/models"))
+            .and(wiremock::matchers::header("Authorization", "Bearer gsk-1"))
+            .respond_with(wiremock::ResponseTemplate::new(200).set_body_json(
+                serde_json::json!({ "data": [
+                    { "id": "llama-3.3-70b-versatile", "object": "model" },
+                    { "id": "whisper-large-v3", "object": "model" }
+                ]}),
+            ))
+            .expect(1)
+            .mount(&platform_server)
+            .await;
+        let modelsdev_server = wiremock::MockServer::start().await;
+        wiremock::Mock::given(wiremock::matchers::method("GET"))
+            .and(wiremock::matchers::path("/api.json"))
+            .respond_with(wiremock::ResponseTemplate::new(200).set_body_json(
+                serde_json::json!({ "groq": { "models": {
+                    "llama-3.3-70b-versatile": {
+                        "limit": {"context": 131072, "output": 32768},
+                        "tool_call": true
+                    },
+                    "whisper-large-v3": { "limit": {"context": 448} }
+                }}}),
+            ))
+            .expect(1)
+            .mount(&modelsdev_server)
+            .await;
+        let cache_dir = tempfile::tempdir().unwrap();
+        let _base =
+            kigi_test_support::EnvGuard::set(kigi_models::GROQ_BASE_URL_ENV, platform_server.uri());
+        let _mdev = kigi_test_support::EnvGuard::set(
+            crate::agent::enrichment_fetch::MODELS_DEV_URL_ENV,
+            format!("{}/api.json", modelsdev_server.uri()),
+        );
+        let _mdev_cache = kigi_test_support::EnvGuard::set(
+            crate::agent::enrichment_fetch::MODELS_DEV_CACHE_DIR_ENV,
+            cache_dir.path(),
+        );
+        let endpoints = crate::agent::config::EndpointsConfig::default();
+        let keys = crate::agent::models::PlatformApiKeys::test_single(
+            kigi_models::PlatformId::Groq,
+            "gsk-1",
+        );
+        let result = tokio::task::spawn_blocking(move || {
+            fetch_platform_models_blocking(&endpoints, None, &keys)
+        })
+        .await
+        .unwrap()
+        .expect("fetch must succeed");
+        assert_eq!(
+            result
+                .models
+                .iter()
+                .map(|m| m.id.as_deref().unwrap_or_default())
+                .collect::<Vec<_>>(),
+            vec!["groq/llama-3.3-70b-versatile"],
+            "whisper (enrichment-known, not tool-calling) must be dropped"
+        );
+        let entry = &result.models[0];
+        assert_eq!(entry.context_window.get(), 131_072);
+        assert_eq!(entry.max_completion_tokens, Some(32_768));
+        let model_entry = crate::agent::config::ModelEntry::from_config_entry(entry);
+        let creds = crate::agent::config::ResolvedCredentials {
+            api_key: Some("gsk-1".into()),
+            base_url: entry.base_url.clone(),
+            auth_type: kigi_chat_state::AuthType::ApiKey,
+            auth_scheme: Default::default(),
+        };
+        let cfg = crate::agent::config::sampling_config_for_model(&model_entry, creds, None);
+        assert_eq!(
+            cfg.chat_compat,
+            kigi_sampling_types::ChatCompat::Passthrough,
+            "groq entries must leave OpenAI-style bodies untouched"
+        );
+    }
+
    #[test]
    fn get_env_keys_parses_strings_and_rejects_non_strings() {
        use crate::agent::config::EnvKeys;