Add Mistral platform + Mistral dialect + array-content handling (provider 5)
The 8th registry row: id "mistral", MISTRAL_API_KEY > auth.json "mistral" scope, https://api.mistral.ai/v1 with KIGI_MISTRAL_BASE_URL override, enrichment-backed metadata with the tool-calling listing restriction (embed/moderation/OCR noise). Mistral is NOT a pure-pattern provider — an adversarial review found two doc-confirmed blockers that no test exercises (no e2e covers a chat POST), so the gate-green registry row alone would have shipped it DOA. A research workflow pinned the exact wire shapes against the mistralai/client-python SDK source (adversarially verified), then both were fixed: 1. stream_options 422: Mistral's strict Pydantic validator rejects the stream_options.include_usage field kigi injects on every streaming request (the SDK's request model has no such field). New ChatCompat::Mistral dialect strips it (plus the kigi-private message fields, like Passthrough). Streaming usage falls back to token estimation. 2. Reasoning content arrays: Mistral reasoning models return content as Union[str, List[ContentChunk]] on both streaming and non-streaming, which the flat Option<String> path could not decode -> aborted turn. A UNIVERSAL lenient deserializer (#[serde(from = "Raw..")] on ChatResponseMessage + ChatChunkDelta) accepts string-or-array, routing {type:text} chunks to the answer and the nested text of {type:thinking} chunks to reasoning_content, tolerant of the OPEN chunk union (unknown types ignored, never fatal). String content stays byte-identical for every other provider (kimi/deepseek/groq/BYOK). Review refuted all seven attack lines (no regression, no crash, exhaustive) and flagged one coverage gap, now closed: a stream-consumer integration test drives a full thinking -> transition -> answer chunk sequence and proves it yields the same reasoning-sibling + assistant-answer result as the reasoning_content string path. Also folds a verified quirk matrix for all 23 remaining API providers into providers-plan.md, tiered by real difficulty (self-enriching OpenRouter/ Vercel; bare-array Together listing; Messages-dialect MiniMax reusing the Anthropic machinery; non-Bearer Azure/Bedrock; router wildcards; the OAuth block).
This commit is contained in:
@@ -595,7 +595,8 @@ mod tests {
|
||||
"openai",
|
||||
"anthropic",
|
||||
"deepseek",
|
||||
"groq"
|
||||
"groq",
|
||||
"mistral"
|
||||
]
|
||||
);
|
||||
assert_eq!(default_id(&built), Some(XAI_API_KEY_METHOD_ID));
|
||||
@@ -625,7 +626,8 @@ mod tests {
|
||||
"openai",
|
||||
"anthropic",
|
||||
"deepseek",
|
||||
"groq"
|
||||
"groq",
|
||||
"mistral"
|
||||
]
|
||||
);
|
||||
assert_eq!(default_id(&built), Some(CACHED_TOKEN_AUTH_METHOD_ID));
|
||||
@@ -648,7 +650,8 @@ mod tests {
|
||||
"openai",
|
||||
"anthropic",
|
||||
"deepseek",
|
||||
"groq"
|
||||
"groq",
|
||||
"mistral"
|
||||
]
|
||||
);
|
||||
assert_eq!(default_id(&built), Some(CACHED_TOKEN_AUTH_METHOD_ID));
|
||||
@@ -674,7 +677,8 @@ mod tests {
|
||||
"openai",
|
||||
"anthropic",
|
||||
"deepseek",
|
||||
"groq"
|
||||
"groq",
|
||||
"mistral"
|
||||
]
|
||||
);
|
||||
assert_eq!(default_id(&built), None);
|
||||
|
||||
@@ -4074,6 +4074,7 @@ pub fn sampling_config_for_model(
|
||||
kigi_models::PlatformChatCompat::Passthrough => {
|
||||
kigi_sampling_types::ChatCompat::Passthrough
|
||||
}
|
||||
kigi_models::PlatformChatCompat::Mistral => kigi_sampling_types::ChatCompat::Mistral,
|
||||
})
|
||||
.unwrap_or_default();
|
||||
SamplerConfig {
|
||||
|
||||
@@ -1206,6 +1206,90 @@ mod tests {
|
||||
);
|
||||
}
|
||||
|
||||
/// Mistral-cycle e2e: embed pollution restricted away, and the Mistral
|
||||
/// dialect (strips stream_options, handles reasoning arrays) is mapped.
|
||||
#[tokio::test(flavor = "multi_thread")]
|
||||
#[serial_test::serial]
|
||||
async fn mistral_listing_restricts_and_maps_mistral_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 msk-1"))
|
||||
.respond_with(wiremock::ResponseTemplate::new(200).set_body_json(
|
||||
serde_json::json!({ "data": [
|
||||
{ "id": "devstral-latest", "object": "model" },
|
||||
{ "id": "mistral-embed", "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!({ "mistral": { "models": {
|
||||
"devstral-latest": {
|
||||
"limit": {"context": 262144, "output": 65536},
|
||||
"tool_call": true
|
||||
},
|
||||
"mistral-embed": { "limit": {"context": 8000} }
|
||||
}}}),
|
||||
))
|
||||
.expect(1)
|
||||
.mount(&modelsdev_server)
|
||||
.await;
|
||||
let cache_dir = tempfile::tempdir().unwrap();
|
||||
let _base = kigi_test_support::EnvGuard::set(
|
||||
kigi_models::MISTRAL_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::Mistral,
|
||||
"msk-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!["mistral/devstral-latest"],
|
||||
"embed (enrichment-known, not tool-calling) must be dropped"
|
||||
);
|
||||
let entry = &result.models[0];
|
||||
assert_eq!(entry.context_window.get(), 262_144);
|
||||
assert_eq!(entry.max_completion_tokens, Some(65_536));
|
||||
let model_entry = crate::agent::config::ModelEntry::from_config_entry(entry);
|
||||
let creds = crate::agent::config::ResolvedCredentials {
|
||||
api_key: Some("msk-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::Mistral,
|
||||
"mistral entries must map to the Mistral dialect (stream_options strip)"
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn get_env_keys_parses_strings_and_rejects_non_strings() {
|
||||
use crate::agent::config::EnvKeys;
|
||||
|
||||
Reference in New Issue
Block a user