Merge remote-tracking branch 'upstream/main' into dev

Author: github-actions[bot]

ROADMAP.md

@@ -14,6 +14,11 @@ const CONTEXT_WINDOW_ERROR_MARKERS: &[&str] = &[
     "too many tokens",
     "prompt is too long",
     "input is too long",
+    "input tokens exceed",
+    "configured limit",
+    "messages resulted in",
+    "completion tokens",
+    "prompt tokens",
     "request is too large",
 ];
 
@@ -542,6 +547,26 @@ mod tests {
         assert_eq!(error.request_id(), Some("req_ctx_123"));
     }
 
+    #[test]
+    fn classifies_openai_configured_limit_errors_as_context_window_failures() {
+        let error = ApiError::Api {
+            status: reqwest::StatusCode::BAD_REQUEST,
+            error_type: Some("invalid_request_error".to_string()),
+            message: Some(
+                "Input tokens exceed the configured limit of 922000 tokens. Your messages resulted in 1860900 tokens. Please reduce the length of the messages."
+                    .to_string(),
+            ),
+            request_id: Some("req_ctx_openai_123".to_string()),
+            body: String::new(),
+            retryable: false,
+            suggested_action: None,
+        };
+
+        assert!(error.is_context_window_failure());
+        assert_eq!(error.safe_failure_class(), "context_window");
+        assert_eq!(error.request_id(), Some("req_ctx_openai_123"));
+    }
+
     #[test]
     fn missing_credentials_without_hint_renders_the_canonical_message() {
         // given

rust/crates/api/src/error.rs

@@ -21,11 +21,12 @@ pub use prompt_cache::{
 pub use providers::anthropic::{AnthropicClient, AnthropicClient as ApiClient, AuthSource};
 pub use providers::openai_compat::{
     build_chat_completion_request, flatten_tool_result_content, is_reasoning_model,
-    model_rejects_is_error_field, translate_message, OpenAiCompatClient, OpenAiCompatConfig,
+    model_rejects_is_error_field, model_requires_reasoning_content_in_history, translate_message,
+    OpenAiCompatClient, OpenAiCompatConfig,
 };
 pub use providers::{
     detect_provider_kind, max_tokens_for_model, max_tokens_for_model_with_override,
-    resolve_model_alias, ProviderKind,
+    model_family_identity_for, model_family_identity_for_kind, resolve_model_alias, ProviderKind,
 };
 pub use sse::{parse_frame, SseParser};
 pub use types::{

rust/crates/api/src/lib.rs

@@ -253,19 +253,31 @@ pub fn detect_provider_kind(model: &str) -> ProviderKind {
     ProviderKind::Ollama
 }
 
+#[must_use]
+pub const fn model_family_identity_for_kind(kind: ProviderKind) -> runtime::ModelFamilyIdentity {
+    match kind {
+        ProviderKind::Anthropic => runtime::ModelFamilyIdentity::Claude,
+        ProviderKind::Xai | ProviderKind::OpenAi => runtime::ModelFamilyIdentity::Generic,
+    }
+}
+
+#[must_use]
+pub fn model_family_identity_for(model: &str) -> runtime::ModelFamilyIdentity {
+    model_family_identity_for_kind(detect_provider_kind(model))
+}
+
 #[must_use]
 pub fn max_tokens_for_model(model: &str) -> u32 {
-    model_token_limit(model).map_or_else(
-        || {
-            let canonical = resolve_model_alias(model);
-            if canonical.contains("opus") {
-                32_000
-            } else {
-                64_000
-            }
-        },
-        |limit| limit.max_output_tokens,
-    )
+    let canonical = resolve_model_alias(model);
+    let heuristic = if canonical.contains("opus") {
+        32_000
+    } else {
+        64_000
+    };
+
+    model_token_limit(model)
+        .map(|limit| heuristic.min(limit.max_output_tokens))
+        .unwrap_or(heuristic)
 }
 
 /// Returns the effective max output tokens for a model, preferring a plugin
@@ -279,7 +291,8 @@ pub fn max_tokens_for_model_with_override(model: &str, plugin_override: Option<u
 #[must_use]
 pub fn model_token_limit(model: &str) -> Option<ModelTokenLimit> {
     let canonical = resolve_model_alias(model);
-    match canonical.as_str() {
+    let base_model = canonical.rsplit('/').next().unwrap_or(canonical.as_str());
+    match base_model {
         "claude-opus-4-6" => Some(ModelTokenLimit {
             max_output_tokens: 32_000,
             context_window_tokens: 200_000,
@@ -292,6 +305,20 @@ pub fn model_token_limit(model: &str) -> Option<ModelTokenLimit> {
             max_output_tokens: 64_000,
             context_window_tokens: 131_072,
         }),
+        // GPT-4.1 family via the OpenAI API.
+        "gpt-4.1" | "gpt-4.1-mini" | "gpt-4.1-nano" => Some(ModelTokenLimit {
+            max_output_tokens: 32_768,
+            context_window_tokens: 1_047_576,
+        }),
+        // GPT-5.4 family via the OpenAI API.
+        "gpt-5.4" => Some(ModelTokenLimit {
+            max_output_tokens: 128_000,
+            context_window_tokens: 1_000_000,
+        }),
+        "gpt-5.4-mini" | "gpt-5.4-nano" => Some(ModelTokenLimit {
+            max_output_tokens: 128_000,
+            context_window_tokens: 400_000,
+        }),
         // Kimi models via DashScope (Moonshot AI)
         // Source: https://platform.moonshot.cn/docs/intro
         "kimi-k2.5" | "kimi-k1.5" => Some(ModelTokenLimit {
@@ -473,8 +500,8 @@ mod tests {
     use super::{
         anthropic_missing_credentials, anthropic_missing_credentials_hint, detect_provider_kind,
         load_dotenv_file, max_tokens_for_model, max_tokens_for_model_with_override,
-        model_token_limit, parse_dotenv, preflight_message_request, resolve_model_alias,
-        ProviderKind,
+        model_family_identity_for, model_family_identity_for_kind, model_token_limit, parse_dotenv,
+        preflight_message_request, resolve_model_alias, ProviderKind,
     };
 
     /// Serializes every test in this module that mutates process-wide
@@ -533,6 +560,42 @@ mod tests {
         );
     }
 
+    #[test]
+    fn maps_provider_kind_to_model_family_identity() {
+        // given: each supported provider kind
+        let anthropic = ProviderKind::Anthropic;
+        let openai = ProviderKind::OpenAi;
+        let xai = ProviderKind::Xai;
+
+        // when: converting provider kinds to prompt model family identities
+        let anthropic_identity = model_family_identity_for_kind(anthropic);
+        let openai_identity = model_family_identity_for_kind(openai);
+        let xai_identity = model_family_identity_for_kind(xai);
+
+        // then: Anthropic stays Claude and OpenAI-compatible providers are generic
+        assert_eq!(anthropic_identity, runtime::ModelFamilyIdentity::Claude);
+        assert_eq!(openai_identity, runtime::ModelFamilyIdentity::Generic);
+        assert_eq!(xai_identity, runtime::ModelFamilyIdentity::Generic);
+    }
+
+    #[test]
+    fn maps_model_name_to_model_family_identity() {
+        // given: Anthropic, OpenAI-compatible, and xAI model names
+        let claude_model = "claude-opus-4-6";
+        let openai_model = "openai/gpt-4.1-mini";
+        let xai_model = "grok-3";
+
+        // when: detecting prompt model family identities from model names
+        let claude_identity = model_family_identity_for(claude_model);
+        let openai_identity = model_family_identity_for(openai_model);
+        let xai_identity = model_family_identity_for(xai_model);
+
+        // then: Anthropic stays Claude and OpenAI-compatible providers are generic
+        assert_eq!(claude_identity, runtime::ModelFamilyIdentity::Claude);
+        assert_eq!(openai_identity, runtime::ModelFamilyIdentity::Generic);
+        assert_eq!(xai_identity, runtime::ModelFamilyIdentity::Generic);
+    }
+
     #[test]
     fn openai_namespaced_model_routes_to_openai_not_anthropic() {
         // Regression: "openai/gpt-4.1-mini" was misrouted to Anthropic when
@@ -617,6 +680,15 @@ mod tests {
     fn keeps_existing_max_token_heuristic() {
         assert_eq!(max_tokens_for_model("opus"), 32_000);
         assert_eq!(max_tokens_for_model("grok-3"), 64_000);
+        assert_eq!(max_tokens_for_model("gpt-5.4"), 64_000);
+    }
+
+    #[test]
+    fn caps_default_max_tokens_to_openai_model_limits() {
+        assert_eq!(max_tokens_for_model("gpt-4.1-mini"), 32_768);
+        assert_eq!(max_tokens_for_model("openai/gpt-4.1-mini"), 32_768);
+        assert_eq!(max_tokens_for_model("gpt-5.4"), 64_000);
+        assert_eq!(max_tokens_for_model("openai/gpt-5.4"), 64_000);
     }
 
     #[test]
@@ -683,6 +755,18 @@ mod tests {
                 .context_window_tokens,
             131_072
         );
+        assert_eq!(
+            model_token_limit("openai/gpt-4.1-mini")
+                .expect("openai/gpt-4.1-mini should be registered")
+                .context_window_tokens,
+            1_047_576
+        );
+        assert_eq!(
+            model_token_limit("gpt-5.4")
+                .expect("gpt-5.4 should be registered")
+                .context_window_tokens,
+            1_000_000
+        );
     }
 
     #[test]
@@ -731,6 +815,42 @@ mod tests {
         }
     }
 
+    #[test]
+    fn preflight_blocks_oversized_requests_for_gpt_5_4() {
+        let request = MessageRequest {
+            model: "gpt-5.4".to_string(),
+            max_tokens: 64_000,
+            messages: vec![InputMessage {
+                role: "user".to_string(),
+                content: vec![InputContentBlock::Text {
+                    text: "x".repeat(3_900_000),
+                }],
+            }],
+            system: Some("Keep the answer short.".to_string()),
+            tools: None,
+            tool_choice: None,
+            stream: true,
+            ..Default::default()
+        };
+
+        let error = preflight_message_request(&request)
+            .expect_err("oversized gpt-5.4 request should be rejected before the provider call");
+
+        match error {
+            ApiError::ContextWindowExceeded {
+                model,
+                requested_output_tokens,
+                context_window_tokens,
+                ..
+            } => {
+                assert_eq!(model, "gpt-5.4");
+                assert_eq!(requested_output_tokens, 64_000);
+                assert_eq!(context_window_tokens, 1_000_000);
+            }
+            other => panic!("expected context-window preflight failure, got {other:?}"),
+        }
+    }
+
     #[test]
     fn preflight_skips_unknown_models() {
         let request = MessageRequest {