Add DeepSeek platform + ChatCompletions dialect system (provider 3)
The 6th registry row: id "deepseek", DEEPSEEK_API_KEY > auth.json "deepseek" scope, base https://api.deepseek.com (chat rides {base}/chat/completions per official docs) with KIGI_DEEPSEEK_BASE_URL override, enrichment-backed metadata (1M context, 384k output cap, high/max effort menu). Structural fix the cycle exposed: kigi's Kimi-specific body adaptation ran UNCONDITIONALLY on every ChatCompletions request. New ChatCompat dialect, declared per platform row and threaded through SamplerConfig, ClientDefaults, and the session-persisted SamplingConfig (serde-default Kimi keeps restored pre-field sessions and BYOK endpoints byte-identical; production persist seams copy it; subagents inherit it): - Kimi: full legacy pipeline (dispatch ≡ legacy pinned) - DeepSeek: thinking:{type, reasoning_effort} per api-docs.deepseek.com (server maps low/medium→high, xhigh→max itself; none disables; absent leaves the server default) - Passthrough: OpenAI-style reasoning_effort scalar untouched (unblocks Groq and the rest of the OpenAI-compatible list) Review-confirmed release blocker fixed: kigi replays Kimi's reasoning_content (and its private model_id) on input assistant messages — Kimi consumes these, but DeepSeek documents input reasoning_content as prefix-mode-only (historically a 400) and other providers don't know either field. The DeepSeek and Passthrough arms now strip both; Kimi's own pipeline is untouched. Pinned on both message shapes.
This commit is contained in:
@@ -1022,6 +1022,107 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// DeepSeek-cycle e2e: bare OpenAI-shape listing + enrichment efforts
|
||||
/// (high/max) produce ChatCompletions entries whose sampler config
|
||||
/// speaks the DeepSeek thinking dialect.
|
||||
#[tokio::test(flavor = "multi_thread")]
|
||||
#[serial_test::serial]
|
||||
async fn deepseek_listing_enriches_and_maps_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 sk-ds"))
|
||||
.respond_with(wiremock::ResponseTemplate::new(200).set_body_json(
|
||||
serde_json::json!({ "data": [
|
||||
{ "id": "deepseek-v4-pro", "object": "model", "owned_by": "deepseek" }
|
||||
]}),
|
||||
))
|
||||
.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!({ "deepseek": { "models": { "deepseek-v4-pro": {
|
||||
"reasoning": true,
|
||||
"reasoning_options": [
|
||||
{"type": "toggle"},
|
||||
{"type": "effort", "values": ["high", "max"]}
|
||||
],
|
||||
"limit": {"context": 1000000, "output": 384000},
|
||||
"tool_call": true
|
||||
}}}}),
|
||||
))
|
||||
.expect(1)
|
||||
.mount(&modelsdev_server)
|
||||
.await;
|
||||
let cache_dir = tempfile::tempdir().unwrap();
|
||||
let _base = kigi_test_support::EnvGuard::set(
|
||||
kigi_models::DEEPSEEK_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::DeepSeek,
|
||||
"sk-ds",
|
||||
);
|
||||
let result = tokio::task::spawn_blocking(move || {
|
||||
fetch_platform_models_blocking(&endpoints, None, &keys)
|
||||
})
|
||||
.await
|
||||
.unwrap()
|
||||
.expect("fetch must succeed");
|
||||
assert_eq!(result.models.len(), 1);
|
||||
let entry = &result.models[0];
|
||||
assert_eq!(entry.id.as_deref(), Some("deepseek/deepseek-v4-pro"));
|
||||
assert_eq!(entry.context_window.get(), 1_000_000);
|
||||
assert_eq!(entry.max_completion_tokens, Some(384_000));
|
||||
assert_eq!(
|
||||
entry.api_backend,
|
||||
crate::sampling::ApiBackend::ChatCompletions
|
||||
);
|
||||
assert_eq!(
|
||||
entry
|
||||
.reasoning_efforts
|
||||
.iter()
|
||||
.map(|o| o.id.as_str())
|
||||
.collect::<Vec<_>>(),
|
||||
vec!["high", "max"]
|
||||
);
|
||||
|
||||
// The managed id maps to the DeepSeek chat dialect; a BYOK entry
|
||||
// (no managed key) keeps the historical Kimi adaptation.
|
||||
let model_entry = crate::agent::config::ModelEntry::from_config_entry(entry);
|
||||
let creds = crate::agent::config::ResolvedCredentials {
|
||||
api_key: Some("sk-ds".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::DeepSeek);
|
||||
let mut byok = entry.clone();
|
||||
byok.id = Some("my-custom".into());
|
||||
let byok_entry = crate::agent::config::ModelEntry::from_config_entry(&byok);
|
||||
let creds = crate::agent::config::ResolvedCredentials {
|
||||
api_key: Some("sk-x".into()),
|
||||
base_url: byok.base_url.clone(),
|
||||
auth_type: kigi_chat_state::AuthType::ApiKey,
|
||||
auth_scheme: Default::default(),
|
||||
};
|
||||
let cfg = crate::agent::config::sampling_config_for_model(&byok_entry, creds, None);
|
||||
assert_eq!(cfg.chat_compat, kigi_sampling_types::ChatCompat::Kimi);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn get_env_keys_parses_strings_and_rejects_non_strings() {
|
||||
use crate::agent::config::EnvKeys;
|
||||
|
||||
Reference in New Issue
Block a user