i/Aether
1
0
Fork 0
mirror of https://github.com/fawney19/Aether.git synced 2026-10-06 01:17:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #876 from MMEXA/codex/cli-alignment-20261001

Browse Source 
对齐 Codex CLI 0.159.3 的画像、模型能力与原生协议
This commit is contained in:
ZheFox
2026-10-05 12:01:34 +08:00
committed by GitHub
parent 54fbcc25a1 e1dadf5b06
commit bda0d4e44d
45 changed files with 1987 additions and 411 deletions
Download Patch File Download Diff File Expand all files Collapse all files
Cargo.lock
Generated
+79 -39
View File
@@ -55,7 +55,7 @@ dependencies = [
"aether-provider-pool",
"aether-provider-transport",
"axum",
"base64",
"base64 0.22.1",
"chrono",
"http",
"regex",
@@ -82,8 +82,9 @@ name = "aether-ai-formats"
version = "0.1.0"
dependencies = [
"aether-contracts",
"base64",
"base64 0.22.1",
"http",
"os_info",
"regex",
"serde",
"serde_json",
@@ -103,7 +104,7 @@ dependencies = [
"aether-pool-core",
"aether-scheduler-core",
"async-trait",
"base64",
"base64 0.22.1",
"http",
"serde",
"serde_json",
@@ -134,7 +135,7 @@ name = "aether-contracts"
version = "0.1.0"
dependencies = [
"aes-gcm",
"base64",
"base64 0.22.1",
"bytes",
"flate2",
"hmac",
@@ -151,7 +152,7 @@ version = "0.1.0"
dependencies = [
"aes",
"aws-lc-rs",
"base64",
"base64 0.22.1",
"cbc",
"hmac",
"pbkdf2",
@@ -193,7 +194,7 @@ dependencies = [
"aether-contracts",
"aether-routing-core",
"async-trait",
"base64",
"base64 0.22.1",
"bcrypt",
"chrono",
"chrono-tz",
@@ -294,7 +295,7 @@ dependencies = [
"async-trait",
"aws-lc-rs",
"axum",
"base64",
"base64 0.22.1",
"bcrypt",
"brotli",
"bytes",
@@ -389,7 +390,7 @@ version = "0.1.0"
dependencies = [
"aether-admission-core",
"aether-contracts",
"base64",
"base64 0.22.1",
"bytes",
"http",
"serde",
@@ -477,7 +478,7 @@ dependencies = [
"aether-scheduler-core",
"async-trait",
"aws-lc-rs",
"base64",
"base64 0.22.1",
"regex",
"serde_json",
"tokio",
@@ -491,7 +492,7 @@ version = "0.1.0"
dependencies = [
"aether-contracts",
"async-trait",
"base64",
"base64 0.22.1",
"http",
"reqwest 0.12.28",
"serde",
@@ -548,7 +549,7 @@ dependencies = [
"async-trait",
"aws-lc-rs",
"axum",
"base64",
"base64 0.22.1",
"chrono",
"crypto_box",
"ed25519-dalek",
@@ -682,7 +683,7 @@ dependencies = [
"anyhow",
"arc-swap",
"axum",
"base64",
"base64 0.22.1",
"bytes",
"clap",
"crossterm 0.28.1",
@@ -733,7 +734,7 @@ dependencies = [
"aether-data-contracts",
"aether-runtime-state",
"async-trait",
"base64",
"base64 0.22.1",
"futures-util",
"serde",
"serde_json",
@@ -850,7 +851,7 @@ version = "1.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "40c48f72fd53cd289104fc64099abca73db4166ad86ea0b4341abe65af83dadc"
dependencies = [
"windows-sys 0.60.2",
"windows-sys 0.61.2",
]
[[package]]
@@ -861,7 +862,7 @@ checksum = "291e6a250ff86cd4a820112fb8898808a366d8f9f58ce16d1f538353ad55747d"
dependencies = [
"anstyle",
"once_cell_polyfill",
"windows-sys 0.60.2",
"windows-sys 0.61.2",
]
[[package]]
@@ -1031,7 +1032,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "8b52af3cb4058c895d37317bb27508dccc8e5f2d39454016b297bf4a400597b8"
dependencies = [
"axum-core",
"base64",
"base64 0.22.1",
"bytes",
"form_urlencoded",
"futures-util",
@@ -1094,6 +1095,12 @@ version = "0.22.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "72b3254f16251a8381aa12e40e3c4d2f0199f8c6508fbecb9d91f575e0fbb8c6"
[[package]]
name = "base64"
version = "0.23.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ac07cdecf99051d9a5238b80f35af32cdeba5b336e55d957b318b50137e18da5"
[[package]]
name = "base64ct"
version = "1.8.3"
@@ -1106,7 +1113,7 @@ version = "0.16.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2b1866ecef4f2d06a0bb77880015fdf2b89e25a1c2e5addacb87e459c86dc67e"
dependencies = [
"base64",
"base64 0.22.1",
"blowfish",
"getrandom 0.2.17",
"subtle",
@@ -1982,7 +1989,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "39cab71617ae0d63f51a36d69f866391735b51691dbda63cf6f96d042b63efeb"
dependencies = [
"libc",
"windows-sys 0.59.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -2579,7 +2586,7 @@ version = "0.1.20"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "96547c2556ec9d12fb1578c4eaf448b04993e7fb79cbaad930a656880a6bdfa0"
dependencies = [
"base64",
"base64 0.22.1",
"bytes",
"futures-channel",
"futures-util",
@@ -2590,7 +2597,7 @@ dependencies = [
"libc",
"percent-encoding",
"pin-project-lite",
"socket2 0.5.10",
"socket2 0.6.3",
"tokio",
"tower-layer",
"tower-service",
@@ -2737,12 +2744,12 @@ dependencies = [
[[package]]
name = "indexmap"
version = "2.13.0"
version = "2.14.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7714e70437a7dc3ac8eb7e6f8df75fd8eb422675fc7678aff7364301092b1017"
checksum = "cc4e190f5d26ca7051642629da2c52fc03bde85a03197c99408dcd291734c855"
dependencies = [
"equivalent",
"hashbrown 0.16.1",
"hashbrown 0.17.1",
"serde",
"serde_core",
]
@@ -3225,7 +3232,7 @@ version = "0.50.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "7957b9740744892f114936ab4a57b3f487491bbeafaf8083688b16841a4240e5"
dependencies = [
"windows-sys 0.59.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -3318,7 +3325,7 @@ checksum = "d354792e39fa5f0009e47623cf8b15b099bf9a652fa55c6f817fe28ac84fea50"
dependencies = [
"async-trait",
"aws-lc-rs",
"base64",
"base64 0.22.1",
"bytes",
"chrono",
"crc-fast",
@@ -3334,7 +3341,7 @@ dependencies = [
"md-5 0.11.0",
"parking_lot",
"percent-encoding",
"quick-xml",
"quick-xml 0.41.0",
"rand 0.10.2",
"reqwest 0.13.4",
"rustls-pki-types",
@@ -3402,6 +3409,17 @@ dependencies = [
"num-traits",
]
[[package]]
name = "os_info"
version = "3.12.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d0e1ac5fde8d43c34139135df8ea9ee9465394b2d8d20f032d38998f64afffc3"
dependencies = [
"log",
"plist",
"windows-sys 0.52.0",
]
[[package]]
name = "palette"
version = "0.7.7"
@@ -3647,6 +3665,19 @@ version = "0.2.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b4596b6d070b27117e987119b4dac604f3c58cfb0b191112e24771b2faeac1a6"
[[package]]
name = "plist"
version = "1.10.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2896bade328c13f7042a297ea5ac5b0951f6cf989dea5f32c2fd98da398195cb"
dependencies = [
"base64 0.23.1",
"indexmap",
"quick-xml 0.42.0",
"serde",
"time",
]
[[package]]
name = "poly1305"
version = "0.8.0"
@@ -3729,6 +3760,15 @@ dependencies = [
"serde",
]
[[package]]
name = "quick-xml"
version = "0.42.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "41b1177fdf999d2321d3fb46ff47159d9c1fb9ad66a4879f8c50a0b504615e9b"
dependencies = [
"memchr",
]
[[package]]
name = "quinn"
version = "0.11.9"
@@ -3742,7 +3782,7 @@ dependencies = [
"quinn-udp",
"rustc-hash",
"rustls",
"socket2 0.5.10",
"socket2 0.6.3",
"thiserror 2.0.18",
"tokio",
"tracing",
@@ -3780,7 +3820,7 @@ dependencies = [
"cfg_aliases",
"libc",
"once_cell",
"socket2 0.5.10",
"socket2 0.6.3",
"tracing",
"windows-sys 0.60.2",
]
@@ -4079,7 +4119,7 @@ version = "0.12.28"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "eddd3ca559203180a307f12d114c268abf583f59b03cb906fd0b3ff8646c1147"
dependencies = [
"base64",
"base64 0.22.1",
"bytes",
"futures-core",
"futures-util",
@@ -4121,7 +4161,7 @@ version = "0.13.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "219c5811de6525e5416c7d5d53bb656d3afdbc6c5af816e0802bcfa42dbdc1c3"
dependencies = [
"base64",
"base64 0.22.1",
"bytes",
"futures-core",
"futures-util",
@@ -4235,7 +4275,7 @@ dependencies = [
"errno",
"libc",
"linux-raw-sys 0.12.1",
"windows-sys 0.59.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -4294,7 +4334,7 @@ dependencies = [
"security-framework",
"security-framework-sys",
"webpki-root-certs",
"windows-sys 0.59.0",
"windows-sys 0.61.2",
]
[[package]]
@@ -4620,7 +4660,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "3a766e1110788c36f4fa1c2b71b387a7815aa65f88ce0229841826633d93723e"
dependencies = [
"libc",
"windows-sys 0.60.2",
"windows-sys 0.61.2",
]
[[package]]
@@ -4667,7 +4707,7 @@ version = "0.8.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "ee6798b1838b6a0f69c007c133b8df5866302197e404e8b6ee8ed3e3a5e68dc6"
dependencies = [
"base64",
"base64 0.22.1",
"bigdecimal",
"bytes",
"chrono",
@@ -4744,7 +4784,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa003f0038df784eb8fecbbac13affe3da23b45194bd57dba231c8f48199c526"
dependencies = [
"atoi",
"base64",
"base64 0.22.1",
"bigdecimal",
"bitflags 2.13.1",
"byteorder",
@@ -4788,7 +4828,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "db58fcd5a53cf07c184b154801ff91347e4c30d17a3562a635ff028ad5deda46"
dependencies = [
"atoi",
"base64",
"base64 0.22.1",
"bigdecimal",
"bitflags 2.13.1",
"byteorder",
@@ -4979,7 +5019,7 @@ dependencies = [
"parking_lot",
"rustix 1.1.4",
"signal-hook",
"windows-sys 0.60.2",
"windows-sys 0.61.2",
]
[[package]]
@@ -5010,7 +5050,7 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4676b37242ccbd1aabf56edb093a4827dc49086c0ffd764a5705899e0f35f8f7"
dependencies = [
"anyhow",
"base64",
"base64 0.22.1",
"bitflags 2.13.1",
"fancy-regex",
"filedescriptor",
@@ -6007,7 +6047,7 @@ version = "0.1.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c2a7b1c03c876122aa43f3020e6c3c3ee5c05081c9a00739faf7503aeba10d22"
dependencies = [
"windows-sys 0.48.0",
"windows-sys 0.61.2",
]
[[package]]
apps/aether-gateway/.aether-windsurf-binary-test-03d740bc-64f1-49cb-b13d-4e5234e5de31/language-server
-1
View File
@@ -1 +0,0 @@
test binary
apps/aether-gateway/src/ai_serving/planner/common.rs
+6 -6
View File
@@ -19,12 +19,12 @@ pub(crate) use crate::ai_serving::{
GEMINI_FILES_UPLOAD_PLAN_KIND, GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND,
GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_CHAT_STREAM_PLAN_KIND, OPENAI_CHAT_SYNC_PLAN_KIND,
OPENAI_EMBEDDING_SYNC_PLAN_KIND, OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND,
OPENAI_RERANK_SYNC_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND, OPENAI_RESPONSES_STREAM_PLAN_KIND,
OPENAI_RESPONSES_SYNC_PLAN_KIND, OPENAI_SEARCH_SYNC_PLAN_KIND,
OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND, OPENAI_VIDEO_CONTENT_PLAN_KIND,
OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND,
OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
OPENAI_MEMORIES_SYNC_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
OPENAI_RESPONSES_STREAM_PLAN_KIND, OPENAI_RESPONSES_SYNC_PLAN_KIND,
OPENAI_SEARCH_SYNC_PLAN_KIND, OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND,
OPENAI_VIDEO_CONTENT_PLAN_KIND, OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND,
OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND, OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
};
pub(crate) use aether_ai_serving::AiRequestedModelFamily as RequestedModelFamily;
apps/aether-gateway/src/ai_serving/planner/decision/control_plan.rs
+10 -7
View File
@@ -6,12 +6,13 @@ use crate::ai_serving::planner::common::{
GEMINI_FILES_DOWNLOAD_PLAN_KIND, GEMINI_FILES_GET_PLAN_KIND, GEMINI_FILES_LIST_PLAN_KIND,
GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND, GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND,
OPENAI_CHAT_STREAM_PLAN_KIND, OPENAI_CHAT_SYNC_PLAN_KIND, OPENAI_EMBEDDING_SYNC_PLAN_KIND,
OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
OPENAI_RESPONSES_STREAM_PLAN_KIND, OPENAI_RESPONSES_SYNC_PLAN_KIND,
OPENAI_SEARCH_SYNC_PLAN_KIND, OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND,
OPENAI_VIDEO_CONTENT_PLAN_KIND, OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND,
OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND, OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_MEMORIES_SYNC_PLAN_KIND,
OPENAI_RERANK_SYNC_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND, OPENAI_RESPONSES_STREAM_PLAN_KIND,
OPENAI_RESPONSES_SYNC_PLAN_KIND, OPENAI_SEARCH_SYNC_PLAN_KIND,
OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND, OPENAI_VIDEO_CONTENT_PLAN_KIND,
OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND,
OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
};
use crate::ai_serving::planner::plan_builders::{
build_gemini_stream_plan_from_decision, build_gemini_sync_plan_from_decision,
@@ -101,7 +102,9 @@ fn build_sync_plan_payload_from_decision(
OPENAI_RESPONSES_SYNC_PLAN_KIND => {
build_openai_responses_sync_plan_from_decision(parts, body_json, payload, false)?
}
OPENAI_IMAGE_SYNC_PLAN_KIND | OPENAI_SEARCH_SYNC_PLAN_KIND => {
OPENAI_IMAGE_SYNC_PLAN_KIND
| OPENAI_SEARCH_SYNC_PLAN_KIND
| OPENAI_MEMORIES_SYNC_PLAN_KIND => {
build_passthrough_sync_plan_from_decision(parts, payload)?
}
OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND => {
apps/aether-gateway/src/ai_serving/planner/decision_input.rs
+31 -4
View File
@@ -17,7 +17,7 @@ use crate::ai_serving::transport::ProviderOutboundRequestContext;
use crate::ai_serving::{
ClientSurface, ExecutionRuntimeAuthContext, GatewayAuthApiKeySnapshot,
GatewayCredentialCarrier, GatewayProviderTransportSnapshot, PlannerAppState,
CODEX_RESPONSES_LITE_HEADER,
CODEX_RESPONSES_LITE_HEADER, OPENAI_MEMORIES_SYNC_PLAN_KIND,
};
use crate::cache::CacheLoadObserver;
use crate::client_session_affinity::client_session_affinity_from_api_request;
@@ -123,6 +123,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
transport: Option<&GatewayProviderTransportSnapshot>,
websocket_continuation: bool,
) -> Result<(), GatewayError> {
let native_memories = decision.decision_kind.as_deref() == Some(OPENAI_MEMORIES_SYNC_PLAN_KIND);
let provider_api_format = decision
.provider_api_format
.clone()
@@ -150,7 +151,12 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
input.requested_model.as_str(),
)
});
crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
if native_memories {
decision
.provider_request_headers
.retain(|name, _| !name.eq_ignore_ascii_case(CODEX_RESPONSES_LITE_HEADER));
} else {
crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
&mut decision.provider_request_headers,
decision.provider_request_body.as_ref(),
provider_type.as_str(),
@@ -159,6 +165,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
input.requested_model.as_str(),
model_capabilities.as_ref(),
);
}
let Some(context) = input.routing_context.as_ref() else {
// Cache identity headers are projected only at the terminal boundary. Any non-empty
@@ -260,7 +267,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
provider_headers.insert(HeaderName::from_static(name), value);
}
}
if original_provider_request_body.is_some() {
if original_provider_request_body.is_some() && !native_memories {
let provider_model = provider_request_body
.get("model")
.and_then(Value::as_str)
@@ -318,6 +325,12 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
}
.map_err(|_| invalid_routing_provider_contract())?;
}
if native_memories {
crate::ai_serving::transport::enforce_same_format_provider_api_operation_body_policy(
&mut provider_request_body,
Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize),
);
}
let provider_model = provider_request_body
.get("model")
.and_then(Value::as_str)
@@ -339,7 +352,11 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
provider_type.as_str(),
provider_api_format.as_str(),
);
crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
if native_memories {
provider_request_headers
.retain(|name, _| !name.eq_ignore_ascii_case(CODEX_RESPONSES_LITE_HEADER));
} else {
crate::ai_serving::apply_codex_openai_responses_lite_header_for_request_body_with_capabilities(
&mut provider_request_headers,
Some(&provider_request_body),
provider_type.as_str(),
@@ -348,6 +365,7 @@ pub(crate) fn apply_provider_request_routing_policy_to_decision_with_websocket_m
input.requested_model.as_str(),
model_capabilities.as_ref(),
);
}
crate::ai_serving::apply_codex_openai_compact_terminal_headers(
&mut provider_request_headers,
provider_type.as_str(),
@@ -382,6 +400,15 @@ fn apply_provider_outbound_request_policies_to_decision(
let Some(context) = input.provider_outbound_context.as_ref() else {
return;
};
let native_context;
let context = if decision.decision_kind.as_deref() == Some(OPENAI_MEMORIES_SYNC_PLAN_KIND) {
native_context = context
.clone()
.with_api_operation(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize);
&native_context
} else {
context
};
let results = crate::ai_serving::transport::apply_provider_outbound_request_policies(
transport,
provider_api_format,
apps/aether-gateway/src/ai_serving/planner/passthrough/provider/family/request.rs
+14 -3
View File
@@ -24,7 +24,9 @@ use crate::ai_serving::transport::{
SameFormatProviderCompatibilityEditAction, SameFormatProviderHeadersInput,
GEMINI_CLI_USER_AGENT, GROK_CHAT_PATH,
};
use crate::ai_serving::{CandidateFailureDiagnostic, GatewayProviderTransportSnapshot};
use crate::ai_serving::{
CandidateFailureDiagnostic, GatewayProviderTransportSnapshot, CODEX_RESPONSES_LITE_HEADER,
};
use crate::{AppState, GatewayError};
mod policy;
@@ -255,7 +257,9 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
// re-enforce stream-field policy afterward.
// Kiro behavior classification already hard-requires upstream streaming,
// and the Kiro envelope does not use a top-level body stream field.
if prepared.kiro_auth.is_none() {
if prepared.kiro_auth.is_none()
&& spec.operation != Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize)
{
enforce_provider_body_stream_policy(
&mut base_provider_request_body,
prepared.provider_api_format.as_str(),
@@ -275,7 +279,8 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
prepared.mapped_model.as_str(),
source_model,
);
if let Err(violation) =
if spec.operation != Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize) {
if let Err(violation) =
crate::ai_serving::finalize_openai_provider_request_with_codex_model_capabilities_and_reasoning_replay_policy(
&mut base_provider_request_body,
crate::ai_serving::OpenAiProviderRequestFinalization {
@@ -313,6 +318,7 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
.await;
return Ok(None);
}
}
// Same-format requests skip `apply_transport_request_body_semantics`, so the opt-in
// Claude Code body mimicry has to be applied here as well.
@@ -597,6 +603,11 @@ pub(crate) async fn resolve_local_same_format_provider_candidate_payload_parts(
source_model,
codex_model_capabilities.as_ref(),
);
if spec.operation == Some(crate::ai_serving::ApiOperation::OpenAiMemoriesSummarize) {
provider_request_headers
.retain(|name, _| !name.eq_ignore_ascii_case(CODEX_RESPONSES_LITE_HEADER));
provider_request_headers.insert("accept".to_string(), "application/json".to_string());
}
crate::ai_serving::transport::xai::insert_cli_identity_headers_if_needed(
transport.as_ref(),
prepared.provider_api_format.as_str(),
apps/aether-gateway/src/ai_serving/planner/passthrough/provider/request/body.rs
+2 -1
View File
@@ -3,7 +3,7 @@ use serde_json::Value;
use super::super::LocalSameFormatProviderSpec;
use crate::ai_serving::transport::{
build_same_format_provider_request_body as build_same_format_provider_request_body_impl,
build_same_format_provider_request_body_with_compatibility_report_and_reasoning_replay_policy as build_same_format_provider_request_body_with_compatibility_report_impl,
build_same_format_provider_request_body_for_operation as build_same_format_provider_request_body_with_compatibility_report_impl,
SameFormatProviderFamily, SameFormatProviderRequestBodyInput,
SameFormatProviderRequestBodyOutput,
};
@@ -69,6 +69,7 @@ pub(crate) fn build_same_format_provider_request_body_with_compatibility_report(
enable_model_directives,
},
reasoning_replay_policy,
spec.operation,
)
}
apps/aether-gateway/src/ai_serving/pure/mod.rs
+1 -1
View File
@@ -163,7 +163,7 @@ pub(crate) use aether_ai_formats::api::{
OPENAI_EMBEDDING_SYNC_PLAN_KIND, OPENAI_IMAGE_STREAM_PLAN_KIND,
OPENAI_IMAGE_STREAM_SUCCESS_REPORT_KIND, OPENAI_IMAGE_SYNC_FINALIZE_REPORT_KIND,
OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_IMAGE_SYNC_SUCCESS_REPORT_KIND,
OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_MEMORIES_SYNC_PLAN_KIND, OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_SUCCESS_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_ERROR_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_FINALIZE_REPORT_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
apps/aether-gateway/src/ai_serving/transport.rs
+1 -1
View File
@@ -78,7 +78,7 @@ pub(crate) use aether_provider_transport::{
build_local_openai_chat_upstream_url, build_local_openai_responses_upstream_url,
build_openai_image_headers, build_openai_image_upstream_url, build_passthrough_headers,
build_request_trace_proxy_value, build_same_format_provider_headers,
build_same_format_provider_request_body,
build_same_format_provider_request_body, build_same_format_provider_request_body_for_operation,
build_same_format_provider_request_body_with_compatibility_report,
build_same_format_provider_request_body_with_compatibility_report_and_reasoning_replay_policy,
build_same_format_provider_upstream_url, build_standard_plan_fallback_headers,
apps/aether-gateway/src/constants.rs
+1
View File
@@ -126,6 +126,7 @@ pub(crate) const RUST_FRONTDOOR_OWNED_ROUTE_PATTERNS: &[&str] = &[
"/v1/messages/count_tokens",
"/v1/responses",
"/v1/responses/compact",
"/v1/memories/trace_summarize",
"/v1/realtime",
"/v1/realtime/calls",
"/v1/live",
apps/aether-gateway/src/control/route/ai.rs
+5
View File
@@ -88,6 +88,11 @@ pub(super) fn classify_ai_public_route(
true,
))
}
} else if method == http::Method::POST && normalized_path == "/v1/memories/trace_summarize" {
Some(
classified("ai_public", "openai", "memories", "openai:responses", true)
.with_api_operation(ApiOperation::OpenAiMemoriesSummarize),
)
} else if method == http::Method::POST && normalized_path == "/v1/alpha/search" {
Some(classified(
"ai_public",
apps/aether-gateway/src/execution_runtime/fallback.rs
+9
View File
@@ -191,6 +191,7 @@ pub(crate) fn resolve_core_sync_error_finalize_report_kind(
let report_kind = match plan_kind {
"openai_chat_sync" => "openai_chat_sync_finalize",
"openai_responses_sync" => "openai_responses_sync_finalize",
"openai_memories_sync" => "openai_memories_sync_finalize",
"openai_responses_compact_sync" => "openai_responses_compact_sync_finalize",
"claude_chat_sync" => "claude_chat_sync_finalize",
"gemini_chat_sync" => "gemini_chat_sync_finalize",
@@ -576,6 +577,14 @@ mod tests {
error: None,
};
assert_eq!(
resolve_core_sync_error_finalize_report_kind(
"openai_memories_sync",
&result,
Some(&serde_json::json!({"error":{"message":"synthetic"}}))
),
Some("openai_memories_sync_finalize".to_string())
);
for body_json in [
serde_json::json!({"status": "failed", "error": null}),
serde_json::json!({"type": "error"}),
apps/aether-gateway/src/frontdoor_loop_guard.rs
+1
View File
@@ -45,6 +45,7 @@ pub(crate) fn frontdoor_self_loop_public_ai_path(path: &str) -> bool {
| "/v1/rerank"
| "/v1/responses"
| "/v1/responses/compact"
| "/v1/memories/trace_summarize"
| "/v1/realtime"
| "/v1/realtime/calls"
| "/v1/live"
apps/aether-gateway/src/handlers/proxy/websocket/responses/adapter.rs
+4 -3
View File
@@ -2,6 +2,7 @@
use async_trait::async_trait;
use serde_json::Value;
use std::borrow::Cow;
use super::adapters::CODEX_RESPONSES_WEBSOCKET_ADAPTER;
use crate::ai_serving::AiExecutionDecision;
@@ -59,7 +60,7 @@ pub(super) enum ResponsesWebSocketRelayDirective<'a> {
ForwardOriginal,
/// The provider frame was a private batch envelope. Forward each retained
/// event in document order by serializing the complete borrowed value.
ForwardEvents(Vec<&'a Value>),
ForwardEvents(Vec<Cow<'a, Value>>),
/// The entire frame was an explicitly recognized provider-private
/// envelope and therefore has no public event to relay.
SuppressProviderPrivate,
@@ -88,8 +89,8 @@ pub(super) trait ResponsesWebSocketProtocolAdapter: Send + Sync {
/// observably ambiguous to the client.
fn rebind_safety_for_upstream_event(&self, event: &Value) -> ResponsesWebSocketRebindSafety;
/// Selects the public relay shape without projecting a provider event
/// through an Aether-owned field or event-type allowlist.
/// 公开事件保持完整；提供商私有元数据仅投影到客户端使用的公开字段，
/// 不公开账户信息。
fn relay_directive_for_upstream_event<'a>(
&self,
_event: &'a Value,
apps/aether-gateway/src/handlers/proxy/websocket/responses/adapters/codex.rs
+92 -4
View File
@@ -2,6 +2,7 @@
use async_trait::async_trait;
use serde_json::{Map, Value};
use std::borrow::Cow;
use super::super::adapter::{
is_standard_responses_event, ResponsesWebSocketAdapterObservation,
@@ -222,7 +223,7 @@ fn codex_relay_directive(event: &Value) -> ResponsesWebSocketRelayDirective<'_>
Some(Value::Array(chunks)) if is_explicit_codex_batch_envelope(event) => {
let public_events = chunks
.iter()
.filter(|chunk| !is_codex_private_leaf_event(chunk))
.filter_map(codex_public_event)
.collect::<Vec<_>>();
if public_events.is_empty() {
ResponsesWebSocketRelayDirective::SuppressProviderPrivate
@@ -233,13 +234,51 @@ fn codex_relay_directive(event: &Value) -> ResponsesWebSocketRelayDirective<'_>
// A malformed or future shape is not proven private. Preserve it
// opaquely rather than guessing at a provider schema.
Some(_) => ResponsesWebSocketRelayDirective::ForwardOriginal,
None if is_codex_private_leaf_event(event) => {
ResponsesWebSocketRelayDirective::SuppressProviderPrivate
}
None if is_codex_private_leaf_event(event) => match codex_public_event(event) {
Some(projected) => ResponsesWebSocketRelayDirective::ForwardEvents(vec![projected]),
None => ResponsesWebSocketRelayDirective::SuppressProviderPrivate,
},
None => ResponsesWebSocketRelayDirective::ForwardOriginal,
}
}
fn codex_public_event(event: &Value) -> Option<Cow<'_, Value>> {
if !is_codex_private_leaf_event(event) {
return Some(Cow::Borrowed(event));
}
if event.get("type").and_then(Value::as_str) != Some("codex.response.metadata") {
// 配额属于选中的上游账户，不能代表网关用户配额；仅交给
// 账户级熔断和持久化路径处理。
return None;
}
let headers = event.get("headers")?.as_object()?;
let public_headers: Map<String, Value> = headers
.iter()
.filter_map(|(name, value)| {
let name = name.to_ascii_lowercase();
if matches!(
name.as_str(),
"x-models-etag"
| "x-codex-turn-state"
| "openai-model"
| "x-codex-safety-buffering-enabled"
| "x-codex-safety-buffering-faster-model"
) && value.as_str().is_some()
{
Some((name, value.clone()))
} else {
None
}
})
.collect();
if public_headers.is_empty() {
return None;
}
Some(Cow::Owned(serde_json::json!({
"type": "codex.response.metadata", "headers": public_headers
})))
}
/// Recognizes only Codex's private batch container. A type-less object must
/// contain exactly `chunks`; unknown siblings could be future public protocol
/// data and therefore force opaque forwarding. A named Codex private root may
@@ -549,6 +588,55 @@ mod tests {
}
}
#[test]
fn codex_metadata_relays_cli_catalog_and_turn_state_without_account_fields() {
let event = json!({
"type": "codex.response.metadata",
"headers": {
"X-Models-Etag": "catalog-v2",
"x-codex-turn-state": "synthetic-turn-state",
"openai-model": "gpt-6.1-sol",
"x-codex-safety-buffering-enabled": "true",
"x-codex-safety-buffering-faster-model": "gpt-6-luna",
"chatgpt-account-id": "synthetic-private-account",
"set-cookie": "synthetic-private-cookie",
"authorization": "synthetic-private-token"
},
"account_hint": "private",
"metadata": {"user_id": "private"}
});
let ResponsesWebSocketRelayDirective::ForwardEvents(events) =
CodexResponsesWebSocketAdapter.relay_directive_for_upstream_event(&event)
else {
panic!("CLI metadata must reach the client");
};
assert_eq!(events.len(), 1);
assert_eq!(
*events[0],
json!({
"type": "codex.response.metadata",
"headers": {"x-models-etag": "catalog-v2", "x-codex-turn-state": "synthetic-turn-state", "openai-model": "gpt-6.1-sol", "x-codex-safety-buffering-enabled": "true", "x-codex-safety-buffering-faster-model": "gpt-6-luna"}
})
);
}
#[test]
fn codex_batch_retains_safe_metadata_in_public_event_order() {
let event = json!({"chunks": [
{"type": "codex.response.metadata", "headers": {"x-models-etag": "catalog-v3"}},
{"type": "codex.rate_limits", "plan_type": "private-plan"},
{"type": "response.created", "response": {"id": "resp_synthetic"}, "future": 42}
]});
let ResponsesWebSocketRelayDirective::ForwardEvents(events) =
CodexResponsesWebSocketAdapter.relay_directive_for_upstream_event(&event)
else {
panic!("batch must retain public events");
};
assert_eq!(events.len(), 2);
assert_eq!(events[0]["headers"]["x-models-etag"], "catalog-v3");
assert_eq!(events[1]["future"], 42);
}
#[test]
fn mixed_codex_batch_forwards_whole_non_private_events_in_order() {
let adapter = CodexResponsesWebSocketAdapter;
apps/aether-gateway/src/handlers/proxy/websocket/responses/connection.rs
+1
View File
@@ -610,6 +610,7 @@ pub(super) async fn relay_bound_connection(
}
Some(ResponsesWebSocketRelayDirective::ForwardEvents(events)) => {
for event in events {
let event = event.as_ref();
let text = match bound
.redaction_restorer
.restore_provider_frame_text(event)
apps/aether-gateway/src/model_fetch/catalog.rs
+5 -8
View File
@@ -2663,14 +2663,11 @@ mod tests {
assert_eq!(plans.len(), 2);
assert!(plans[0].url.ends_with("/models?client_version=0.145.2"));
assert!(plans[1].url.ends_with("/models?client_version=0.146.0"));
assert_eq!(
plans[0].headers.get("user-agent").map(String::as_str),
Some("codex_cli_rs/0.145.2")
);
assert_eq!(
plans[1].headers.get("user-agent").map(String::as_str),
Some("codex_cli_rs/0.146.0")
);
for (plan, version) in plans.iter().zip(["0.145.2", "0.146.0"]) {
let ua = plan.headers.get("user-agent").expect("画像应包含 UA");
assert!(ua.starts_with(&format!("codex_cli_rs/{version} (")));
assert!(ua.ends_with(") unknown"));
}
let target = target();
assert_ne!(
apps/aether-gateway/src/tests/ai_execute/sync/search.rs
+266 -152
View File
@@ -45,6 +45,153 @@ where
}
}
fn hash_api_key(value: &str) -> String {
let mut hasher = Sha256::new();
hasher.update(value.as_bytes());
format!("{:x}", hasher.finalize())
}
fn auth_snapshot() -> StoredAuthApiKeySnapshot {
StoredAuthApiKeySnapshot::new(
"user-search-1".to_string(),
"alice".to_string(),
Some("[email protected]".to_string()),
"user".to_string(),
"local".to_string(),
true,
false,
Some(json!(["openai", "codex"])),
Some(json!(["openai:responses"])),
None,
"api-key-search-1".to_string(),
Some("search-client".to_string()),
true,
false,
false,
Some(60),
Some(5),
Some(4_102_444_800_i64),
Some(json!(["openai", "codex"])),
Some(json!(["openai:responses"])),
None,
)
.expect("auth snapshot should build")
}
fn candidate_row(api_format: &str) -> StoredMinimalCandidateSelectionRow {
StoredMinimalCandidateSelectionRow {
provider_id: "provider-codex-search-1".to_string(),
provider_name: "codex".to_string(),
provider_type: "codex".to_string(),
provider_priority: 10,
provider_is_active: true,
endpoint_id: "endpoint-codex-search-1".to_string(),
endpoint_api_format: api_format.to_string(),
endpoint_api_family: Some("openai".to_string()),
endpoint_kind: Some(api_format.split_once(':').expect("format").1.to_string()),
endpoint_is_active: true,
key_id: "key-codex-search-1".to_string(),
key_name: "oauth".to_string(),
key_auth_type: "oauth".to_string(),
key_is_active: true,
key_api_formats: Some(vec!["openai:responses".to_string()]),
key_allowed_models: None,
key_capabilities: None,
key_internal_priority: 5,
key_global_priority_by_format: Some(json!({"openai:search": 1})),
model_id: "model-codex-search-1".to_string(),
global_model_id: "global-model-codex-search-1".to_string(),
global_model_name: "gpt-5.6-sol".to_string(),
global_model_mappings: None,
global_model_supports_streaming: Some(false),
model_provider_model_name: "gpt-5.6-sol".to_string(),
model_provider_model_mappings: Some(vec![StoredProviderModelMapping {
name: "gpt-5.6-sol".to_string(),
priority: 1,
api_formats: Some(vec!["openai:responses".to_string()]),
endpoint_ids: None,
operations: None,
}]),
model_supports_streaming: Some(false),
model_is_active: true,
model_is_available: true,
}
}
fn provider() -> StoredProviderCatalogProvider {
StoredProviderCatalogProvider::new(
"provider-codex-search-1".to_string(),
"codex".to_string(),
Some("https://chatgpt.com".to_string()),
"codex".to_string(),
)
.expect("provider should build")
.with_transport_fields(
true,
false,
false,
None,
Some(1),
None,
Some(900.0),
None,
None,
)
}
fn endpoint(api_format: &str) -> StoredProviderCatalogEndpoint {
StoredProviderCatalogEndpoint::new(
"endpoint-codex-search-1".to_string(),
"provider-codex-search-1".to_string(),
api_format.to_string(),
Some("openai".to_string()),
Some(api_format.split_once(':').expect("format").1.to_string()),
true,
)
.expect("endpoint should build")
.with_transport_fields(
"https://chatgpt.com/backend-api/codex".to_string(),
None,
None,
Some(1),
None,
None,
None,
None,
)
.expect("endpoint transport should build")
}
fn key() -> StoredProviderCatalogKey {
let auth_config = encrypt_python_fernet_plaintext(
DEVELOPMENT_ENCRYPTION_KEY,
r#"{"provider_type":"codex","account_id":"account-search-1","is_fedramp":true}"#,
)
.expect("auth config should encrypt");
StoredProviderCatalogKey::new(
"key-codex-search-1".to_string(),
"provider-codex-search-1".to_string(),
"oauth".to_string(),
"oauth".to_string(),
None,
true,
)
.expect("key should build")
.with_transport_fields(
Some(json!(["openai:responses"])),
encrypt_python_fernet_plaintext(DEVELOPMENT_ENCRYPTION_KEY, "codex-search-access-token")
.expect("access token should encrypt"),
Some(auth_config),
None,
Some(json!({"openai:search": 1})),
None,
Some(4_102_444_800),
None,
None,
)
.expect("key transport should build")
}
#[test]
fn gateway_executes_codex_search_with_responses_permission_and_search_contract() {
run_search_sync_test(
@@ -54,156 +201,6 @@ fn gateway_executes_codex_search_with_responses_permission_and_search_contract()
}
async fn gateway_executes_codex_search_with_responses_permission_and_search_contract_impl() {
fn hash_api_key(value: &str) -> String {
let mut hasher = Sha256::new();
hasher.update(value.as_bytes());
format!("{:x}", hasher.finalize())
}
fn auth_snapshot() -> StoredAuthApiKeySnapshot {
StoredAuthApiKeySnapshot::new(
"user-search-1".to_string(),
"alice".to_string(),
Some("[email protected]".to_string()),
"user".to_string(),
"local".to_string(),
true,
false,
Some(json!(["openai", "codex"])),
Some(json!(["openai:responses"])),
None,
"api-key-search-1".to_string(),
Some("search-client".to_string()),
true,
false,
false,
Some(60),
Some(5),
Some(4_102_444_800_i64),
Some(json!(["openai", "codex"])),
Some(json!(["openai:responses"])),
None,
)
.expect("auth snapshot should build")
}
fn candidate_row() -> StoredMinimalCandidateSelectionRow {
StoredMinimalCandidateSelectionRow {
provider_id: "provider-codex-search-1".to_string(),
provider_name: "codex".to_string(),
provider_type: "codex".to_string(),
provider_priority: 10,
provider_is_active: true,
endpoint_id: "endpoint-codex-search-1".to_string(),
endpoint_api_format: "openai:search".to_string(),
endpoint_api_family: Some("openai".to_string()),
endpoint_kind: Some("search".to_string()),
endpoint_is_active: true,
key_id: "key-codex-search-1".to_string(),
key_name: "oauth".to_string(),
key_auth_type: "oauth".to_string(),
key_is_active: true,
key_api_formats: Some(vec!["openai:responses".to_string()]),
key_allowed_models: None,
key_capabilities: None,
key_internal_priority: 5,
key_global_priority_by_format: Some(json!({"openai:search": 1})),
model_id: "model-codex-search-1".to_string(),
global_model_id: "global-model-codex-search-1".to_string(),
global_model_name: "gpt-5.6-sol".to_string(),
global_model_mappings: None,
global_model_supports_streaming: Some(false),
model_provider_model_name: "gpt-5.6-sol".to_string(),
model_provider_model_mappings: Some(vec![StoredProviderModelMapping {
name: "gpt-5.6-sol".to_string(),
priority: 1,
api_formats: Some(vec!["openai:responses".to_string()]),
endpoint_ids: None,
operations: None,
}]),
model_supports_streaming: Some(false),
model_is_active: true,
model_is_available: true,
}
}
fn provider() -> StoredProviderCatalogProvider {
StoredProviderCatalogProvider::new(
"provider-codex-search-1".to_string(),
"codex".to_string(),
Some("https://chatgpt.com".to_string()),
"codex".to_string(),
)
.expect("provider should build")
.with_transport_fields(
true,
false,
false,
None,
Some(1),
None,
Some(900.0),
None,
None,
)
}
fn endpoint() -> StoredProviderCatalogEndpoint {
StoredProviderCatalogEndpoint::new(
"endpoint-codex-search-1".to_string(),
"provider-codex-search-1".to_string(),
"openai:search".to_string(),
Some("openai".to_string()),
Some("search".to_string()),
true,
)
.expect("endpoint should build")
.with_transport_fields(
"https://chatgpt.com/backend-api/codex".to_string(),
None,
None,
Some(1),
None,
None,
None,
None,
)
.expect("endpoint transport should build")
}
fn key() -> StoredProviderCatalogKey {
let auth_config = encrypt_python_fernet_plaintext(
DEVELOPMENT_ENCRYPTION_KEY,
r#"{"provider_type":"codex","account_id":"account-search-1","is_fedramp":true}"#,
)
.expect("auth config should encrypt");
StoredProviderCatalogKey::new(
"key-codex-search-1".to_string(),
"provider-codex-search-1".to_string(),
"oauth".to_string(),
"oauth".to_string(),
None,
true,
)
.expect("key should build")
.with_transport_fields(
Some(json!(["openai:responses"])),
encrypt_python_fernet_plaintext(
DEVELOPMENT_ENCRYPTION_KEY,
"codex-search-access-token",
)
.expect("access token should encrypt"),
Some(auth_config),
None,
Some(json!({"openai:search": 1})),
None,
Some(4_102_444_800),
None,
None,
)
.expect("key transport should build")
}
let seen_plans = Arc::new(Mutex::new(Vec::<serde_json::Value>::new()));
let seen_plans_clone = Arc::clone(&seen_plans);
let execution_runtime = Router::new().route(
@@ -316,7 +313,7 @@ async fn gateway_executes_codex_search_with_responses_permission_and_search_cont
auth_snapshot(),
)]));
let candidate_repository = Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed({
let primary = candidate_row();
let primary = candidate_row("openai:search");
let mut backup = primary.clone();
backup.provider_id = "provider-codex-search-2".to_string();
backup.provider_name = "codex-backup".to_string();
@@ -338,7 +335,7 @@ async fn gateway_executes_codex_search_with_responses_permission_and_search_cont
vec![primary, backup]
},
{
let primary = endpoint();
let primary = endpoint("openai:search");
let mut backup = primary.clone();
backup.id = "endpoint-codex-search-2".to_string();
backup.provider_id = "provider-codex-search-2".to_string();
@@ -598,3 +595,120 @@ async fn gateway_executes_codex_search_with_responses_permission_and_search_cont
gateway_handle.abort();
execution_runtime_handle.abort();
}
#[test]
fn gateway_executes_codex_memories_with_responses_permission_and_native_json() {
run_search_sync_test(
"gateway_executes_codex_memories_with_responses_permission_and_native_json",
|| async {
let response_body = json!({"output":[{"trace_summary":"synthetic trace", "memory_summary":"synthetic memory"}],"future_response_field":{"enabled":true}});
let seen = Arc::new(Mutex::new(None));
let captured = Arc::clone(&seen);
let expected = response_body.clone();
let runtime = Router::new().route("/v1/execute/sync", any(move |request: Request| {
let captured = Arc::clone(&captured);
let response_body = expected.clone();
async move {
let bytes = to_bytes(request.into_body(), usize::MAX).await.expect("read plan");
let plan: serde_json::Value = serde_json::from_slice(&bytes).expect("parse plan");
let request_id = plan["request_id"].clone();
*captured.lock().expect("capture lock") = Some(plan);
let (status_code, response_body) = if request_id == json!("trace-memory-error") {
(400, json!({"error":{"type":"invalid_request_error","message":"synthetic invalid trace","code":"invalid_trace"},"future_error_field":{"enabled":true}}))
} else { (200, response_body) };
Json(json!({"request_id":request_id,"status_code":status_code,"headers":{"content-type":"application/json"},"body":{"json_body":response_body},"telemetry":{"elapsed_ms":1}}))
}
}));
let client_key = "sk-synthetic-memory-client";
let auth = Arc::new(InMemoryAuthApiKeySnapshotRepository::seed(vec![(
Some(hash_api_key(client_key)),
auth_snapshot(),
)]));
let candidates = Arc::new(InMemoryMinimalCandidateSelectionReadRepository::seed(vec![
candidate_row("openai:responses"),
]));
let mut memory_provider = provider();
memory_provider.config = Some(
json!({"codex":{"fingerprint_convergence_enabled":true},"failover_rules":{"stop_status_codes":[400]}}),
);
let catalog = Arc::new(InMemoryProviderCatalogReadRepository::seed(
vec![memory_provider],
vec![endpoint("openai:responses")],
vec![key()],
));
let request_candidates = Arc::new(InMemoryRequestCandidateRepository::default());
let data = crate::data::GatewayDataState::with_auth_candidate_selection_provider_catalog_and_request_candidate_repository_for_tests(auth,candidates,catalog,Arc::clone(&request_candidates),DEVELOPMENT_ENCRYPTION_KEY)
.with_system_config_values_for_tests([(crate::system_features::ENABLE_MODEL_DIRECTIVES_CONFIG_KEY.to_string(),json!(true))]);
let (runtime_url, runtime_handle) = start_server(runtime).await;
let state = build_state_with_execution_runtime_override(runtime_url)
.with_data_state_for_tests(data);
let (url, gateway_handle) = start_server(build_router_with_state(state)).await;
let input = json!({"model":"gpt-5.6-sol-max","traces":[{"id":"synthetic-trace","metadata":{"source_path":"/synthetic/trace.json"},"items":[{"type":"message","role":"user","content":[]}]}],"reasoning":{"effort":"low"},"future_request_field":{"enabled":true}});
let response = reqwest::Client::new()
.post(format!("{url}/v1/memories/trace_summarize"))
.header(http::header::AUTHORIZATION, format!("Bearer {client_key}"))
.header(TRACE_ID_HEADER, "trace-memory-1")
.json(&input)
.send()
.await
.expect("send request");
let status = response.status();
let body: serde_json::Value = response.json().await.expect("read response");
assert_eq!(status, StatusCode::OK, "{body}");
assert_eq!(body, response_body);
let plan = seen
.lock()
.expect("capture lock")
.clone()
.expect("captured plan");
assert_eq!(
plan["url"],
"https://chatgpt.com/backend-api/codex/memories/trace_summarize"
);
assert_eq!(plan["stream"], false);
assert_eq!(plan["client_api_format"], "openai:responses");
assert_eq!(plan["provider_api_format"], "openai:responses");
assert_eq!(plan["headers"]["originator"], "codex_cli_rs");
assert_eq!(
plan["headers"]["authorization"],
"Bearer codex-search-access-token"
);
assert_eq!(plan["headers"]["accept"], "application/json");
assert!(plan["headers"]
.get("x-openai-internal-codex-responses-lite")
.is_none());
let mut expected_input = input;
expected_input["model"] = json!("gpt-5.6-sol");
expected_input["reasoning"]["effort"] = json!("max");
assert_eq!(plan["body"]["json_body"], expected_input);
let stored = request_candidates
.list_by_request_id("trace-memory-1")
.await
.expect("read candidates");
assert_eq!(stored.len(), 1);
assert_eq!(stored[0].status, RequestCandidateStatus::Success);
let error = reqwest::Client::new()
.post(format!("{url}/v1/memories/trace_summarize"))
.header(http::header::AUTHORIZATION, format!("Bearer {client_key}"))
.header(TRACE_ID_HEADER, "trace-memory-error")
.json(&expected_input)
.send()
.await
.expect("error response");
let error_status = error.status();
assert_eq!(error_status, StatusCode::BAD_REQUEST);
assert_eq!(
error.json::<serde_json::Value>().await.expect("error JSON"),
json!({"error":{"type":"invalid_request_error","message":"synthetic invalid trace","code":"invalid_trace"},"future_error_field":{"enabled":true}})
);
let error_candidates = request_candidates
.list_by_request_id("trace-memory-error")
.await
.expect("error candidate");
assert_eq!(error_candidates.len(), 1);
assert_eq!(error_candidates[0].status, RequestCandidateStatus::Failed);
gateway_handle.abort();
runtime_handle.abort();
},
);
}
apps/aether-gateway/src/tests/control/admin/provider_query.rs
+6
View File
@@ -849,6 +849,12 @@ async fn gateway_handles_admin_provider_query_models_falls_back_to_codex_preset_
"gpt-5.6-luna",
"gpt-5.6-sol",
"gpt-5.6-terra",
"gpt-6-astra",
"gpt-6-luna",
"gpt-6-sol",
"gpt-6.1-sol",
"gpt-daybreak-blue-latest",
"gpt-daybreak-red-latest",
]
);
assert_eq!(
apps/aether-gateway/src/tests/frontdoor/ai.rs
+3 -4
View File
@@ -1270,10 +1270,9 @@ async fn run_versioned_codex_model_cards_frontdoor_scenario() {
captured_catalog_plan.0,
"https://chatgpt.example/backend-api/codex/models?client_version=0.145.2"
);
assert_eq!(
captured_catalog_plan.1.as_deref(),
Some("codex_cli_rs/0.145.2")
);
let captured_ua = captured_catalog_plan.1.expect("目录请求应包含 UA");
assert!(captured_ua.starts_with("codex_cli_rs/0.145.2 ("));
assert!(captured_ua.ends_with(") unknown"));
let fresh_response = client
.get(format!("{gateway_url}/v1/models?client_version=0.145.2"))
crates/aether-ai/formats/Cargo.toml
+1
View File
@@ -10,6 +10,7 @@ description = "Pure AI API format, surface, planning, and finalize logic for Aet
aether-contracts.workspace = true
base64.workspace = true
http.workspace = true
os_info = { version = "=3.12.0", default-features = false }
regex.workspace = true
serde.workspace = true
serde_json.workspace = true
crates/aether-ai/formats/src/api.rs
+1 -1
View File
@@ -33,7 +33,7 @@ pub use crate::contracts::{
OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_STREAM_SUCCESS_REPORT_KIND,
OPENAI_IMAGE_SYNC_ERROR_REPORT_KIND, OPENAI_IMAGE_SYNC_FINALIZE_REPORT_KIND,
OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_IMAGE_SYNC_SUCCESS_REPORT_KIND,
OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_MEMORIES_SYNC_PLAN_KIND, OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_SUCCESS_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_ERROR_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_FINALIZE_REPORT_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
crates/aether-ai/formats/src/codex_profile.rs
+21 -5
View File
@@ -1,4 +1,6 @@
use std::sync::{OnceLock, RwLock};
use std::sync::{LazyLock, OnceLock, RwLock};
static OS_INFO: LazyLock<os_info::Info> = LazyLock::new(os_info::get);
/// 当前支持的 Codex 客户端类型。
#[derive(Clone, Copy, Debug, PartialEq, Eq)]
@@ -32,7 +34,19 @@ impl CodexClientProfile {
Ok(Self {
client_kind: CodexClientKind::Cli,
codex_version: version.to_owned(),
user_agent: format!("{}/{}", originator, version),
// 按 CLI 格式使用当前网关的公开平台信息。无客户端终端时使用官方
// unknown 标识，不复制调用方终端后缀、安装标识或个人身份。
user_agent: format!(
"{}/{} ({} {}; {}) unknown",
originator,
version,
OS_INFO.os_type(),
OS_INFO.version(),
OS_INFO.architecture().unwrap_or(std::env::consts::ARCH),
)
.chars()
.map(|ch| if matches!(ch, ' '..='~') { ch } else { '_' })
.collect(),
originator,
})
}
@@ -40,8 +54,8 @@ impl CodexClientProfile {
impl Default for CodexClientProfile {
fn default() -> Self {
// 远程发布检查不可用时仍保持现有线上行为，避免启动或请求被版本服务拖住。
Self::cli("0.153.4").expect("built-in Codex CLI profile must be valid")
// 最新已核验稳定版本；后台版本刷新继续作为版本真源。
Self::cli("0.159.3").expect("built-in Codex CLI profile must be valid")
}
}
@@ -97,7 +111,9 @@ mod tests {
let profile = CodexClientProfile::cli("0.200.1").expect("valid version");
assert_eq!(profile.client_kind, CodexClientKind::Cli);
assert_eq!(profile.originator, "codex_cli_rs");
assert_eq!(profile.user_agent, "codex_cli_rs/0.200.1");
assert!(profile.user_agent.starts_with("codex_cli_rs/0.200.1 ("));
assert!(profile.user_agent.ends_with(") unknown"));
assert!(profile.user_agent.contains(std::env::consts::ARCH));
}
#[test]
crates/aether-ai/formats/src/contracts/mod.rs
+3 -2
View File
@@ -22,7 +22,7 @@ pub use plan_kinds::{
GEMINI_INTERACTIONS_SYNC_PLAN_KIND, GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND,
GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_CHAT_STREAM_PLAN_KIND, OPENAI_CHAT_SYNC_PLAN_KIND,
OPENAI_EMBEDDING_SYNC_PLAN_KIND, OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND,
OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_MEMORIES_SYNC_PLAN_KIND, OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
OPENAI_RESPONSES_STREAM_PLAN_KIND, OPENAI_RESPONSES_SYNC_PLAN_KIND,
OPENAI_SEARCH_SYNC_PLAN_KIND, OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND,
@@ -49,7 +49,8 @@ pub use report_kinds::{
OPENAI_EMBEDDING_SYNC_ERROR_REPORT_KIND, OPENAI_EMBEDDING_SYNC_FINALIZE_REPORT_KIND,
OPENAI_EMBEDDING_SYNC_SUCCESS_REPORT_KIND, OPENAI_IMAGE_STREAM_SUCCESS_REPORT_KIND,
OPENAI_IMAGE_SYNC_ERROR_REPORT_KIND, OPENAI_IMAGE_SYNC_FINALIZE_REPORT_KIND,
OPENAI_IMAGE_SYNC_SUCCESS_REPORT_KIND, OPENAI_RESPONSES_COMPACT_STREAM_SUCCESS_REPORT_KIND,
OPENAI_IMAGE_SYNC_SUCCESS_REPORT_KIND, OPENAI_MEMORIES_SYNC_SUCCESS_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_STREAM_SUCCESS_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_ERROR_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_FINALIZE_REPORT_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_SUCCESS_REPORT_KIND, OPENAI_RESPONSES_STREAM_SUCCESS_REPORT_KIND,
crates/aether-ai/formats/src/contracts/plan_kinds.rs
+1
View File
@@ -5,6 +5,7 @@ pub const GEMINI_FILES_DELETE_PLAN_KIND: &str = "gemini_files_delete";
pub const GEMINI_FILES_DOWNLOAD_PLAN_KIND: &str = "gemini_files_download";
pub const OPENAI_IMAGE_STREAM_PLAN_KIND: &str = "openai_image_stream";
pub const OPENAI_IMAGE_SYNC_PLAN_KIND: &str = "openai_image_sync";
pub const OPENAI_MEMORIES_SYNC_PLAN_KIND: &str = "openai_memories_sync";
pub const OPENAI_VIDEO_CONTENT_PLAN_KIND: &str = "openai_video_content";
pub const OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND: &str = "openai_video_cancel_sync";
pub const OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND: &str = "openai_video_remix_sync";
crates/aether-ai/formats/src/contracts/report_kinds.rs
+8
View File
@@ -31,6 +31,8 @@ pub const OPENAI_RESPONSES_COMPACT_SYNC_SUCCESS_REPORT_KIND: &str =
"openai_responses_compact_sync_success";
pub const OPENAI_EMBEDDING_SYNC_SUCCESS_REPORT_KIND: &str = "openai_embedding_sync_success";
pub const OPENAI_SEARCH_SYNC_SUCCESS_REPORT_KIND: &str = "openai_search_sync_success";
pub const OPENAI_MEMORIES_SYNC_FINALIZE_REPORT_KIND: &str = "openai_memories_sync_finalize";
pub const OPENAI_MEMORIES_SYNC_SUCCESS_REPORT_KIND: &str = "openai_memories_sync_success";
pub const GEMINI_EMBEDDING_SYNC_SUCCESS_REPORT_KIND: &str = "gemini_embedding_sync_success";
pub const OPENAI_IMAGE_SYNC_SUCCESS_REPORT_KIND: &str = "openai_image_sync_success";
pub const CLAUDE_CLI_SYNC_SUCCESS_REPORT_KIND: &str = "claude_cli_sync_success";
@@ -62,6 +64,9 @@ pub const GEMINI_CLI_SYNC_ERROR_REPORT_KIND: &str = "gemini_cli_sync_error";
pub fn implicit_sync_finalize_report_kind(plan_kind: &str) -> Option<&'static str> {
match plan_kind {
super::plan_kinds::OPENAI_MEMORIES_SYNC_PLAN_KIND => {
Some(OPENAI_MEMORIES_SYNC_FINALIZE_REPORT_KIND)
}
OPENAI_CHAT_SYNC_PLAN_KIND => Some(OPENAI_CHAT_SYNC_FINALIZE_REPORT_KIND),
CLAUDE_CHAT_SYNC_PLAN_KIND => Some(CLAUDE_CHAT_SYNC_FINALIZE_REPORT_KIND),
GEMINI_CHAT_SYNC_PLAN_KIND => Some(GEMINI_CHAT_SYNC_FINALIZE_REPORT_KIND),
@@ -80,6 +85,7 @@ pub fn implicit_sync_finalize_report_kind(plan_kind: &str) -> Option<&'static st
pub fn core_error_default_client_api_format(report_kind: &str) -> Option<&'static str> {
match report_kind {
OPENAI_MEMORIES_SYNC_FINALIZE_REPORT_KIND => Some("openai:responses"),
OPENAI_CHAT_SYNC_FINALIZE_REPORT_KIND => Some("openai:chat"),
CLAUDE_CHAT_SYNC_FINALIZE_REPORT_KIND => Some("claude:messages"),
GEMINI_CHAT_SYNC_FINALIZE_REPORT_KIND => Some("gemini:generate_content"),
@@ -98,6 +104,7 @@ pub fn core_error_default_client_api_format(report_kind: &str) -> Option<&'stati
pub fn core_error_background_report_kind(report_kind: &str) -> Option<&'static str> {
match report_kind {
OPENAI_MEMORIES_SYNC_FINALIZE_REPORT_KIND => Some(OPENAI_RESPONSES_SYNC_ERROR_REPORT_KIND),
OPENAI_CHAT_SYNC_FINALIZE_REPORT_KIND => Some(OPENAI_CHAT_SYNC_ERROR_REPORT_KIND),
CLAUDE_CHAT_SYNC_FINALIZE_REPORT_KIND => Some(CLAUDE_CHAT_SYNC_ERROR_REPORT_KIND),
GEMINI_CHAT_SYNC_FINALIZE_REPORT_KIND => Some(GEMINI_CHAT_SYNC_ERROR_REPORT_KIND),
@@ -124,6 +131,7 @@ pub fn core_error_background_report_kind(report_kind: &str) -> Option<&'static s
pub fn core_success_background_report_kind(report_kind: &str) -> Option<&'static str> {
match report_kind {
OPENAI_MEMORIES_SYNC_FINALIZE_REPORT_KIND => Some(OPENAI_MEMORIES_SYNC_SUCCESS_REPORT_KIND),
OPENAI_CHAT_SYNC_FINALIZE_REPORT_KIND => Some(OPENAI_CHAT_SYNC_SUCCESS_REPORT_KIND),
CLAUDE_CHAT_SYNC_FINALIZE_REPORT_KIND => Some(CLAUDE_CHAT_SYNC_SUCCESS_REPORT_KIND),
GEMINI_CHAT_SYNC_FINALIZE_REPORT_KIND => Some(GEMINI_CHAT_SYNC_SUCCESS_REPORT_KIND),
crates/aether-ai/formats/src/contracts/request_dimensions.rs
+6
View File
@@ -34,6 +34,7 @@ pub enum ApiOperation {
ClaudeMessagesCreate,
ClaudeCountTokens,
OpenAiResponsesCompact,
OpenAiMemoriesSummarize,
}
impl ApiOperation {
@@ -42,6 +43,7 @@ impl ApiOperation {
Self::ClaudeMessagesCreate => "messages",
Self::ClaudeCountTokens => "count_tokens",
Self::OpenAiResponsesCompact => "compact",
Self::OpenAiMemoriesSummarize => "trace_summarize",
}
}
}
@@ -55,5 +57,9 @@ mod tests {
assert_eq!(ClientSurface::ClaudeCode.as_str(), "claude_code");
assert_eq!(ApiOperation::ClaudeMessagesCreate.as_str(), "messages");
assert_eq!(ApiOperation::ClaudeCountTokens.as_str(), "count_tokens");
assert_eq!(
ApiOperation::OpenAiMemoriesSummarize.as_str(),
"trace_summarize"
);
}
}
crates/aether-ai/formats/src/formats/openai/responses/codex.rs
+57 -148
View File
@@ -380,149 +380,22 @@ fn bundled_codex_model_card(spec: BundledCodexModelCardSpec<'_>) -> Value {
})
}
fn bundled_gpt_5_6_codex_model_card(
model_id: &str,
display_name: &str,
description: &str,
default_reasoning_level: &str,
priority: u64,
multi_agent_version: &str,
supports_ultra: bool,
) -> Value {
let mut efforts = vec!["low", "medium", "high", "xhigh", "max"];
if supports_ultra {
efforts.push("ultra");
}
let mut card = bundled_codex_model_card(BundledCodexModelCardSpec {
model_id,
display_name,
description,
default_reasoning_level,
default_reasoning_summary: "none",
use_responses_lite: true,
efforts: &efforts,
default_verbosity: "low",
supports_priority_tier: true,
});
let object = card
.as_object_mut()
.expect("bundled Codex model card must be an object");
object.extend(
json!({
"shell_type": "shell_command",
"supports_image_detail_original": true,
"supports_search_tool": true,
"input_modalities": ["text", "image"],
"context_window": 372_000,
"max_context_window": 372_000,
"comp_hash": "3000",
"experimental_supported_tools": [],
"visibility": "list",
"supported_in_api": true,
"priority": priority,
"additional_speed_tiers": ["fast"],
"multi_agent_version": multi_agent_version,
"tool_mode": "code_mode_only",
"prefer_websockets": true,
"reasoning_summary_format": "experimental",
"include_skills_usage_instructions": false,
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"truncation_policy": { "mode": "tokens", "limit": 10_000 },
"minimal_client_version": "0.144.0",
})
.as_object()
.expect("bundled Codex model card extension must be an object")
.clone(),
);
card
}
fn bundled_codex_auto_review_model_card() -> Value {
let mut card = bundled_codex_model_card(BundledCodexModelCardSpec {
model_id: "codex-auto-review",
display_name: "Codex Auto Review",
description: "Automatic approval review model for Codex.",
default_reasoning_level: "medium",
default_reasoning_summary: "none",
use_responses_lite: false,
efforts: &["low", "medium", "high", "xhigh"],
default_verbosity: "low",
supports_priority_tier: false,
});
let object = card
.as_object_mut()
.expect("bundled Codex model card must be an object");
object.extend(
json!({
"shell_type": "shell_command",
"supports_image_detail_original": true,
"supports_search_tool": true,
"input_modalities": ["text", "image"],
"context_window": 272_000,
"max_context_window": 1_000_000,
"experimental_supported_tools": [],
"visibility": "hide",
"supported_in_api": true,
"priority": 43,
"additional_speed_tiers": [],
"prefer_websockets": true,
"reasoning_summary_format": "experimental",
"include_skills_usage_instructions": false,
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"truncation_policy": { "mode": "tokens", "limit": 10_000 },
"minimal_client_version": "0.98.0",
})
.as_object()
.expect("bundled Codex model card extension must be an object")
.clone(),
);
card
}
pub fn bundled_codex_model_cards() -> &'static [Value] {
static CARDS: OnceLock<Vec<Value>> = OnceLock::new();
CARDS.get_or_init(|| {
vec![
bundled_gpt_5_6_codex_model_card(
"gpt-5.6-sol",
"GPT-5.6-Sol",
"Latest frontier agentic coding model.",
"low",
1,
"v2",
true,
),
bundled_gpt_5_6_codex_model_card(
"gpt-5.6-terra",
"GPT-5.6-Terra",
"Balanced agentic coding model for everyday work.",
"medium",
2,
"v2",
true,
),
bundled_gpt_5_6_codex_model_card(
"gpt-5.6-luna",
"GPT-5.6-Luna",
"Fast and affordable agentic coding model.",
"medium",
3,
"v1",
false,
),
bundled_codex_model_card(BundledCodexModelCardSpec {
model_id: "gpt-5.5",
display_name: "GPT-5.5",
description: "Frontier model for complex coding, research, and real-world work.",
default_reasoning_level: "medium",
default_reasoning_summary: "none",
use_responses_lite: false,
efforts: &["low", "medium", "high", "xhigh"],
default_verbosity: "low",
supports_priority_tier: true,
}),
// 公开能力快照来自 openai/codex rust-v0.159.3 的
// codex-rs/models-manager/models.json；账户远端目录继续优先。
let mut cards: Vec<Value> = serde_json::from_str(include_str!("codex_models_0_159_3.json"))
.expect("bundled Codex model capability snapshot must be valid JSON");
for card in &mut cards {
let object = card.as_object_mut().expect("model card must be an object");
object.insert("id".to_string(), object["slug"].clone());
object.insert("object".to_string(), json!("model"));
object.insert("owned_by".to_string(), json!("openai"));
object.insert("api_formats".to_string(), json!(["openai:responses"]));
}
// 保留现有配置路由使用的旧模型标识。
cards.extend(vec![
bundled_codex_model_card(BundledCodexModelCardSpec {
model_id: "gpt-5.4",
display_name: "GPT-5.4",
@@ -556,8 +429,8 @@ pub fn bundled_codex_model_cards() -> &'static [Value] {
default_verbosity: "low",
supports_priority_tier: false,
}),
bundled_codex_auto_review_model_card(),
]
]);
cards
})
}
@@ -2183,10 +2056,46 @@ mod tests {
#[test]
fn codex_client_user_agent_matches_originator_and_version() {
let profile = crate::codex_client_profile();
assert_eq!(
profile.user_agent,
format!("{}/{}", profile.originator, profile.codex_version)
);
assert!(profile.user_agent.starts_with(&format!(
"{}/{} (",
profile.originator, profile.codex_version
)));
assert!(profile.user_agent.ends_with(") unknown"));
}
#[test]
fn bundled_latest_cli_models_preserve_capabilities_without_account_data() {
for model in ["gpt-6-astra", "gpt-6.1-sol"] {
let card = bundled_codex_model_cards()
.iter()
.find(|card| card["slug"] == model)
.unwrap();
assert_eq!(card["context_window"], 272_000);
assert_eq!(card["max_context_window"], 872_000);
assert_eq!(card["comp_hash"], "3000");
assert_eq!(card["minimal_client_version"], "0.153.0");
assert_eq!(
card["supported_reasoning_levels"]
.as_array()
.unwrap()
.iter()
.map(|level| level["effort"].as_str().unwrap())
.collect::<Vec<_>>(),
["low", "medium", "high", "xhigh", "max", "ultra"]
);
for private in [
"account_id",
"user_id",
"installation_id",
"cookie",
"authorization",
] {
assert!(
card.get(private).is_none(),
"unexpected account field: {private}"
);
}
}
}
#[test]
@@ -2824,7 +2733,7 @@ mod tests {
"codex-auto-review",
None,
);
assert!(!capabilities.use_responses_lite);
assert!(capabilities.use_responses_lite);
assert_eq!(
capabilities.default_reasoning_effort.as_deref(),
Some("medium")
@@ -2832,7 +2741,7 @@ mod tests {
assert_eq!(capabilities.default_reasoning_summary, None);
assert!(capabilities.supports_parallel_tool_calls);
assert_eq!(capabilities.default_verbosity.as_deref(), Some("low"));
assert!(capabilities.supported_service_tiers.is_empty());
assert_eq!(capabilities.supported_service_tiers, vec!["priority"]);
}
#[test]
crates/aether-ai/formats/src/formats/openai/responses/codex_models_0_159_3.json
+963
View File
@@ -0,0 +1,963 @@
[
{
"slug": "gpt-6-astra",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"multi_agent_reasoning_effort": "xhigh",
"use_responses_lite": true,
"supports_reasoning_effort_updates": true,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": false,
"include_plugin_usage_instructions": false,
"guardian": null,
"node_repl_auto_review_required": true,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "GPT-6-Astra",
"description": "Frontier intelligence for the most demanding work.",
"default_reasoning_level": "low",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
},
{
"effort": "ultra",
"description": "Maximum reasoning with automatic task delegation"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.153.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": null,
"priority": 2,
"experimental_supported_tools": [
"send_user_message_async",
"clock"
],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": null,
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "2x speed, increased usage"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-6.1-sol",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"multi_agent_reasoning_effort": "xhigh",
"use_responses_lite": true,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": false,
"include_plugin_usage_instructions": false,
"guardian": null,
"node_repl_auto_review_required": true,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "GPT-6.1-Sol",
"description": "Latest workhorse model for coding and everyday work.",
"default_reasoning_level": "low",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
},
{
"effort": "ultra",
"description": "Maximum reasoning with automatic task delegation"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.153.0",
"supported_in_api": true,
"availability_nux": {
"message": "Maximize usage with GPT-6.1 Sol. Try it on complex work for near-Astra performance at a lower cost."
},
"upgrade": null,
"priority": 1,
"experimental_supported_tools": [
"send_user_message_async",
"clock"
],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": null,
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "2x speed, increased usage"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true,
"supports_reasoning_effort_updates": true
},
{
"slug": "gpt-6-sol",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"multi_agent_reasoning_effort": null,
"use_responses_lite": true,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": false,
"include_plugin_usage_instructions": false,
"guardian": null,
"node_repl_auto_review_required": true,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "GPT-6-Sol",
"description": "Previous generation workhorse model.",
"default_reasoning_level": "medium",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
},
{
"effort": "ultra",
"description": "Maximum reasoning with automatic task delegation"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.155.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": null,
"priority": 3,
"experimental_supported_tools": [
"send_user_message_async",
"clock"
],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": "priority",
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "1.5x speed"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-6-luna",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"multi_agent_reasoning_effort": null,
"use_responses_lite": true,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": false,
"include_plugin_usage_instructions": false,
"guardian": null,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "GPT-6-Luna",
"description": "Fast and affordable model for easier tasks.",
"default_reasoning_level": "medium",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.155.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": null,
"priority": 4,
"experimental_supported_tools": [
"send_user_message_async",
"clock"
],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": "priority",
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "1.5x speed"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-5.6-sol",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"multi_agent_reasoning_effort": null,
"use_responses_lite": true,
"supports_reasoning_effort_updates": false,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": true,
"include_plugin_usage_instructions": true,
"guardian": null,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "GPT-5.6-Sol",
"description": "Older generation workhorse model.",
"default_reasoning_level": "low",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
},
{
"effort": "ultra",
"description": "Maximum reasoning with automatic task delegation"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.144.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": {
"model": "gpt-6-sol",
"migration_markdown": "Meet GPT-6 Sol\n\nOur latest Sol is more intelligent and more efficient so your usage limits go further. This model is a great daily driver for complex tasks, especially coding.\n",
"retirement_at": null
},
"priority": 5,
"experimental_supported_tools": [],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": null,
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "1.5x speed, increased usage"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-5.6-terra",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"multi_agent_reasoning_effort": null,
"use_responses_lite": true,
"supports_reasoning_effort_updates": false,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": true,
"include_plugin_usage_instructions": true,
"guardian": null,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "GPT-5.6-Terra",
"description": "Older balanced model for straightforward work.",
"default_reasoning_level": "medium",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
},
{
"effort": "ultra",
"description": "Maximum reasoning with automatic task delegation"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.144.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": {
"model": "gpt-6-sol",
"migration_markdown": "Meet GPT-6 Sol\n\nOur latest Sol is more intelligent and more efficient so your usage limits go further. This model is a great daily driver for complex tasks, especially coding.\n",
"retirement_at": null
},
"priority": 8,
"experimental_supported_tools": [],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": null,
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "1.5x speed, increased usage"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-5.6-luna",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v1",
"multi_agent_reasoning_effort": null,
"use_responses_lite": true,
"supports_reasoning_effort_updates": false,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": true,
"include_plugin_usage_instructions": true,
"guardian": null,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "GPT-5.6-Luna",
"description": "Older fast and efficient model.",
"default_reasoning_level": "medium",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.144.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": {
"model": "gpt-6-luna",
"migration_markdown": "Meet GPT-6 Luna\n\nOur latest Luna is significantly more efficient, so your usage limits go even further. Reach for it for any job that doesn't require frontier intelligence.\n",
"retirement_at": null
},
"priority": 9,
"experimental_supported_tools": [],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": null,
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "1.5x speed, increased usage"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-daybreak-blue-latest",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"use_responses_lite": true,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": true,
"include_plugin_usage_instructions": true,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"auto_review_model_override": null,
"model_specialty": "cyber",
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "Daybreak Blue",
"description": "Latest frontier agentic coding model for broad defensive cybersecurity work.",
"default_reasoning_level": "low",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
},
{
"effort": "ultra",
"description": "Maximum reasoning with automatic task delegation"
}
],
"shell_type": "shell_command",
"visibility": "hide",
"minimal_client_version": "0.142.2",
"supported_in_api": true,
"availability_nux": null,
"upgrade": null,
"priority": 11,
"experimental_supported_tools": [],
"supports_search_tool": true,
"default_service_tier": null,
"service_tiers": [],
"additional_speed_tiers": [],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-daybreak-red-latest",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "high",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v2",
"use_responses_lite": true,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": false,
"include_plugin_usage_instructions": false,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"auto_review_model_override": null,
"model_specialty": "cyber",
"context_window": 372000,
"max_context_window": 372000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "Daybreak Red",
"description": "Cyber-permissive variant of our latest frontier agentic coding model for advanced, authorized cybersecurity research.",
"default_reasoning_level": "medium",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
},
{
"effort": "ultra",
"description": "Maximum reasoning with automatic task delegation"
}
],
"shell_type": "shell_command",
"visibility": "hide",
"minimal_client_version": "0.142.2",
"supported_in_api": true,
"availability_nux": null,
"upgrade": null,
"priority": 12,
"experimental_supported_tools": [],
"supports_search_tool": true,
"default_service_tier": null,
"service_tiers": [],
"additional_speed_tiers": [],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "gpt-5.5",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": null,
"multi_agent_version": null,
"multi_agent_reasoning_effort": null,
"use_responses_lite": false,
"supports_reasoning_effort_updates": false,
"include_skills_usage_instructions": true,
"include_apps_usage_instructions": true,
"include_plugin_usage_instructions": true,
"guardian": null,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 272000,
"auto_compact_token_limit": null,
"comp_hash": "2911",
"default_reasoning_summary": "none",
"display_name": "GPT-5.5",
"description": "Legacy coding model.",
"default_reasoning_level": "medium",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
}
],
"shell_type": "shell_command",
"visibility": "list",
"minimal_client_version": "0.124.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": {
"model": "gpt-6-sol",
"migration_markdown": "Meet GPT-6 Sol\n\nOur latest Sol is more intelligent and more efficient so your usage limits go further. This model is a great daily driver for complex tasks, especially coding.\n",
"retirement_at": null
},
"priority": 13,
"experimental_supported_tools": [],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": null,
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "1.5x speed, increased usage"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
},
{
"slug": "codex-auto-review",
"prefer_websockets": true,
"support_verbosity": true,
"default_verbosity": "low",
"apply_patch_tool_type": "freeform",
"web_search_tool_type": "text_and_image",
"input_modalities": [
"text",
"image"
],
"supports_image_detail_original": true,
"truncation_policy": {
"mode": "tokens",
"limit": 10000
},
"supports_parallel_tool_calls": true,
"tool_mode": "code_mode_only",
"multi_agent_version": "v1",
"multi_agent_reasoning_effort": null,
"use_responses_lite": true,
"supports_reasoning_effort_updates": false,
"include_skills_usage_instructions": false,
"include_apps_usage_instructions": false,
"include_plugin_usage_instructions": false,
"guardian": null,
"node_repl_auto_review_required": false,
"node_repl_disabled": false,
"requires_sandboxed_review": false,
"auto_review_model_override": null,
"model_specialty": null,
"context_window": 272000,
"max_context_window": 872000,
"auto_compact_token_limit": null,
"comp_hash": "3000",
"default_reasoning_summary": "none",
"display_name": "Codex Auto Review",
"description": "Automatic approval review model for Codex.",
"default_reasoning_level": "medium",
"supported_reasoning_levels": [
{
"effort": "low",
"description": "Fast responses with lighter reasoning"
},
{
"effort": "medium",
"description": "Balances speed and reasoning depth for everyday tasks"
},
{
"effort": "high",
"description": "Greater reasoning depth for complex problems"
},
{
"effort": "xhigh",
"description": "Extra high reasoning depth for complex problems"
},
{
"effort": "max",
"description": "Maximum reasoning depth for the hardest problems"
}
],
"shell_type": "shell_command",
"visibility": "hide",
"minimal_client_version": "0.98.0",
"supported_in_api": true,
"availability_nux": null,
"upgrade": null,
"priority": 43,
"experimental_supported_tools": [],
"supports_search_tool": true,
"supports_experimental_context": false,
"default_service_tier": null,
"service_tiers": [
{
"id": "priority",
"name": "Fast",
"description": "1.5x speed, increased usage"
}
],
"additional_speed_tiers": [
"fast"
],
"supports_reasoning_summary_parameter": true,
"supports_reasoning_summaries": true
}
]
crates/aether-ai/formats/src/formats/shared/passthrough.rs
+21
View File
@@ -7,6 +7,7 @@ use crate::contracts::{
GEMINI_EMBEDDING_SYNC_SUCCESS_REPORT_KIND, GEMINI_INTERACTIONS_STREAM_PLAN_KIND,
GEMINI_INTERACTIONS_STREAM_SUCCESS_REPORT_KIND, GEMINI_INTERACTIONS_SYNC_PLAN_KIND,
GEMINI_INTERACTIONS_SYNC_SUCCESS_REPORT_KIND, OPENAI_EMBEDDING_SYNC_PLAN_KIND,
OPENAI_MEMORIES_SYNC_PLAN_KIND, OPENAI_MEMORIES_SYNC_SUCCESS_REPORT_KIND,
OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND, OPENAI_SEARCH_SYNC_PLAN_KIND,
OPENAI_SEARCH_SYNC_SUCCESS_REPORT_KIND,
};
@@ -29,6 +30,14 @@ pub struct LocalSameFormatProviderSpec {
pub fn resolve_sync_spec(plan_kind: &str) -> Option<LocalSameFormatProviderSpec> {
match plan_kind {
OPENAI_MEMORIES_SYNC_PLAN_KIND => Some(LocalSameFormatProviderSpec {
api_format: "openai:responses",
decision_kind: OPENAI_MEMORIES_SYNC_PLAN_KIND,
report_kind: OPENAI_MEMORIES_SYNC_SUCCESS_REPORT_KIND,
family: LocalSameFormatProviderFamily::Standard,
require_streaming: false,
operation: Some(ApiOperation::OpenAiMemoriesSummarize),
}),
CLAUDE_CHAT_SYNC_PLAN_KIND => Some(LocalSameFormatProviderSpec {
api_format: "claude:messages",
decision_kind: CLAUDE_CHAT_SYNC_PLAN_KIND,
@@ -260,4 +269,16 @@ mod tests {
assert_eq!(spec.report_kind, "openai_search_sync_success");
assert!(!spec.require_streaming);
}
#[test]
fn memories_uses_responses_permissions_and_a_native_sync_operation() {
let spec = resolve_sync_spec("openai_memories_sync").expect("memory spec");
assert_eq!(spec.api_format, "openai:responses");
assert_eq!(
spec.operation,
Some(crate::ApiOperation::OpenAiMemoriesSummarize)
);
assert_eq!(spec.report_kind, "openai_memories_sync_success");
assert!(!spec.require_streaming);
}
}
crates/aether-ai/formats/src/formats/shared/routing.rs
+16 -7
View File
@@ -11,13 +11,13 @@ use crate::contracts::{
GEMINI_INTERACTIONS_STREAM_PLAN_KIND, GEMINI_INTERACTIONS_SYNC_PLAN_KIND,
GEMINI_VIDEO_CANCEL_SYNC_PLAN_KIND, GEMINI_VIDEO_CREATE_SYNC_PLAN_KIND,
OPENAI_CHAT_STREAM_PLAN_KIND, OPENAI_CHAT_SYNC_PLAN_KIND, OPENAI_EMBEDDING_SYNC_PLAN_KIND,
OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_REALTIME_STREAM_PLAN_KIND,
OPENAI_RERANK_SYNC_PLAN_KIND, OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND, OPENAI_RESPONSES_STREAM_PLAN_KIND,
OPENAI_RESPONSES_SYNC_PLAN_KIND, OPENAI_SEARCH_SYNC_PLAN_KIND,
OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND, OPENAI_VIDEO_CONTENT_PLAN_KIND,
OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND, OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND,
OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
OPENAI_IMAGE_STREAM_PLAN_KIND, OPENAI_IMAGE_SYNC_PLAN_KIND, OPENAI_MEMORIES_SYNC_PLAN_KIND,
OPENAI_REALTIME_STREAM_PLAN_KIND, OPENAI_RERANK_SYNC_PLAN_KIND,
OPENAI_RESPONSES_COMPACT_STREAM_PLAN_KIND, OPENAI_RESPONSES_COMPACT_SYNC_PLAN_KIND,
OPENAI_RESPONSES_STREAM_PLAN_KIND, OPENAI_RESPONSES_SYNC_PLAN_KIND,
OPENAI_SEARCH_SYNC_PLAN_KIND, OPENAI_VIDEO_CANCEL_SYNC_PLAN_KIND,
OPENAI_VIDEO_CONTENT_PLAN_KIND, OPENAI_VIDEO_CREATE_SYNC_PLAN_KIND,
OPENAI_VIDEO_DELETE_SYNC_PLAN_KIND, OPENAI_VIDEO_REMIX_SYNC_PLAN_KIND,
};
use crate::formats::openai::image::request::is_openai_image_stream_request;
@@ -193,6 +193,14 @@ pub fn resolve_execution_runtime_sync_plan_kind_with_client_surface(
return None;
}
if route_family == Some("openai")
&& route_kind == Some("memories")
&& *method == Method::POST
&& path == "/v1/memories/trace_summarize"
{
return Some(OPENAI_MEMORIES_SYNC_PLAN_KIND);
}
if route_family == Some("openai")
&& route_kind == Some("video")
&& *method == Method::POST
@@ -580,6 +588,7 @@ pub fn supports_sync_execution_decision_kind(plan_kind: &str) -> bool {
matches!(
plan_kind,
OPENAI_CHAT_SYNC_PLAN_KIND
| OPENAI_MEMORIES_SYNC_PLAN_KIND
| OPENAI_EMBEDDING_SYNC_PLAN_KIND
| OPENAI_RERANK_SYNC_PLAN_KIND
| OPENAI_SEARCH_SYNC_PLAN_KIND
crates/aether-ai/formats/src/formats/shared/sync_products.rs
+22
View File
@@ -746,6 +746,9 @@ fn maybe_build_standard_same_format_sync_body(
}
let body_json = body_json?;
if report_kind == "openai_memories_sync_finalize" {
return Some(body_json.clone());
}
if is_error_like_sync_body(body_json) {
return None;
}
@@ -1949,6 +1952,7 @@ fn is_openai_responses_finalize_kind(report_kind: &str) -> bool {
fn standard_same_format_api_format(report_kind: &str) -> Option<&'static str> {
match report_kind {
"openai_memories_sync_finalize" => Some("openai:responses"),
"openai_chat_sync_finalize" => Some("openai:chat"),
"claude_chat_sync_finalize" => Some("claude:messages"),
"gemini_chat_sync_finalize" => Some("gemini:generate_content"),
@@ -4163,6 +4167,24 @@ mod tests {
use base64::Engine as _;
use serde_json::json;
#[test]
fn native_memories_response_keeps_output_array_and_future_fields() {
let body = json!({"output":[{"trace_summary":"synthetic", "memory_summary":"memory"}], "future_response_field":{"enabled":true}});
let context = json!({"provider_api_format":"openai:responses","client_api_format":"openai:responses","needs_conversion":false,"requested_model":"gpt-6.1-sol-max"});
assert_eq!(
maybe_build_standard_same_format_sync_body_from_normalized_payload(
"openai_memories_sync_finalize",
200,
Some(&context),
Some(&body),
None
)
.expect("native response")
.expect("body"),
body
);
}
#[test]
fn converts_openai_images_sync_body_to_gemini_image_body() {
let provider_body_json = json!({
crates/aether-model-fetch/src/logic.rs
+10 -4
View File
@@ -1860,14 +1860,20 @@ mod tests {
assert_eq!(
model_ids,
vec![
"gpt-6-astra",
"gpt-6.1-sol",
"gpt-6-sol",
"gpt-6-luna",
"gpt-5.6-sol",
"gpt-5.6-terra",
"gpt-5.6-luna",
"gpt-daybreak-blue-latest",
"gpt-daybreak-red-latest",
"gpt-5.5",
"codex-auto-review",
"gpt-5.4",
"gpt-5.4-mini",
"gpt-5.2",
"codex-auto-review",
]
);
let sol = models
@@ -1886,7 +1892,7 @@ mod tests {
);
assert_eq!(sol["multi_agent_version"], "v2");
assert_eq!(sol["supports_image_detail_original"], true);
assert_eq!(sol["context_window"], 372_000);
assert_eq!(sol["context_window"], 272_000);
for model_id in ["gpt-5.6-sol", "gpt-5.6-terra", "gpt-5.6-luna"] {
let model = models
@@ -1898,7 +1904,7 @@ mod tests {
assert_eq!(model["experimental_supported_tools"], json!([]));
assert_eq!(model["tool_mode"], "code_mode_only");
assert_eq!(model["prefer_websockets"], true);
assert_eq!(model["reasoning_summary_format"], "experimental");
assert!(model.get("reasoning_summary_format").is_none());
assert_eq!(model["truncation_policy"]["limit"], 10_000);
assert_eq!(model["minimal_client_version"], "0.144.0");
assert!(model.get("effective_context_window_percent").is_none());
@@ -1924,7 +1930,7 @@ mod tests {
assert_eq!(auto_review["supported_in_api"], true);
assert_eq!(auto_review["default_reasoning_level"], "medium");
assert_eq!(auto_review["default_reasoning_summary"], "none");
assert_eq!(auto_review["use_responses_lite"], false);
assert_eq!(auto_review["use_responses_lite"], true);
}
#[test]
crates/aether-model-fetch/src/transport.rs
+15 -5
View File
@@ -129,6 +129,12 @@ pub async fn build_standard_models_fetch_execution_plan_for_client_version(
provider_type == "codex" && api_format.starts_with("openai:");
let is_deepseek_anthropic_models_fetch = api_format.starts_with("claude:")
&& deepseek_anthropic_models_fetch_uses_openai_auth(&transport.endpoint.base_url);
if is_codex_openai_models_fetch {
if let Some(version) = codex_client_version {
aether_ai_formats::CodexClientProfile::cli(version)
.map_err(|error| error.to_string())?;
}
}
let mut headers =
standard_models_fetch_headers(&api_format, &provider_type, codex_client_version);
if is_codex_openai_models_fetch {
@@ -636,10 +642,9 @@ fn standard_models_fetch_headers(
return BTreeMap::from([
(
"user-agent".to_string(),
format!(
"{}/{client_version}",
aether_ai_formats::codex_client_originator()
),
aether_ai_formats::CodexClientProfile::cli(client_version)
.expect("validated Codex catalog client version")
.user_agent,
),
(
"originator".to_string(),
@@ -1059,7 +1064,12 @@ mod tests {
);
assert_eq!(
plan.headers.get("user-agent").map(String::as_str),
Some("codex_cli_rs/0.145.2")
Some(
aether_ai_formats::CodexClientProfile::cli("0.145.2")
.unwrap()
.user_agent
.as_str()
)
);
assert_eq!(
plan.headers.get("originator").map(String::as_str),
crates/aether-oauth/src/provider/providers/codex.rs
+31
View File
@@ -3,6 +3,16 @@ use super::generic::{
};
use crate::provider::ProviderOAuthAdapter;
/// Codex CLI 的公开 OAuth 权限范围，不包含账户专属值。
pub const CODEX_OAUTH_SCOPES: &[&str] = &[
"openid",
"profile",
"email",
"offline_access",
"api.connectors.read",
"api.connectors.invoke",
];
#[derive(Debug, Clone)]
pub struct CodexProviderOAuthAdapter {
inner: GenericProviderOAuthAdapter,
@@ -45,6 +55,7 @@ impl ProviderOAuthAdapter for CodexProviderOAuthAdapter {
query.append_pair("prompt", "login");
query.append_pair("id_token_add_organizations", "true");
query.append_pair("codex_cli_simplified_flow", "true");
query.append_pair("originator", "codex_cli_rs");
}
response.authorize_url = url.to_string();
Ok(response)
@@ -156,6 +167,26 @@ mod tests {
assert!(response
.authorize_url
.contains("codex_cli_simplified_flow=true"));
let url = url::Url::parse(&response.authorize_url).unwrap();
let query = url.query_pairs().collect::<BTreeMap<_, _>>();
assert_eq!(
query.get("scope").map(|value| value.as_ref()),
Some("openid profile email offline_access api.connectors.read api.connectors.invoke")
);
assert_eq!(
query.get("originator").map(|value| value.as_ref()),
Some("codex_cli_rs")
);
assert_eq!(
query
.get("code_challenge_method")
.map(|value| value.as_ref()),
Some("S256")
);
assert_eq!(
query.get("state").map(|value| value.as_ref()),
Some("state-1")
);
}
#[tokio::test]
crates/aether-oauth/src/provider/providers/generic.rs
+1 -1
View File
@@ -92,7 +92,7 @@ pub const GENERIC_PROVIDER_OAUTH_TEMPLATES: &[GenericProviderOAuthTemplate] = &[
client_id: "app_EMoamEEZ73f0CkXaXp7hrann",
client_id_env: None,
client_secret_env: None,
scopes: &["openid", "email", "profile", "offline_access"],
scopes: super::codex::CODEX_OAUTH_SCOPES,
redirect_uri: "http://localhost:1455/auth/callback",
use_pkce: true,
uses_json_payload: false,
crates/aether-oauth/src/provider/providers/mod.rs
+1 -1
View File
@@ -12,7 +12,7 @@ pub use claude_code::{
CLAUDE_CODE_COOKIE_SCOPE, CLAUDE_CODE_OAUTH_SCOPES, CLAUDE_CODE_PROVIDER_TYPE,
CLAUDE_CODE_REDIRECT_URI, CLAUDE_CODE_TOKEN_URL, CLAUDE_CODE_WEB_BASE_URL,
};
pub use codex::CodexProviderOAuthAdapter;
pub use codex::{CodexProviderOAuthAdapter, CODEX_OAUTH_SCOPES};
pub use generic::{
derive_codex_identity_fingerprint, GenericProviderOAuthAdapter, GenericProviderOAuthTemplate,
ANTIGRAVITY_OAUTH_CLIENT_ID_ENV, ANTIGRAVITY_OAUTH_CLIENT_SECRET_ENV,
crates/aether-provider/transport/src/codex_fingerprint.rs
+30
View File
@@ -107,6 +107,12 @@ pub(crate) fn apply_codex_fingerprint_convergence_policy(
}
let is_responses = aether_ai_formats::is_openai_responses_format(provider_api_format);
if context.api_operation() == Some(aether_ai_formats::ApiOperation::OpenAiMemoriesSummarize) {
return ProviderOutboundRequestPolicyResult::skipped(
policy,
ProviderOutboundRequestPolicyReason::NativeOperationExcluded,
);
}
let is_live = aether_ai_formats::api_format_alias_matches(provider_api_format, "codex:live");
if !is_responses && !is_live {
return ProviderOutboundRequestPolicyResult::skipped(
@@ -567,6 +573,30 @@ mod tests {
}
}
#[test]
fn native_memories_excludes_responses_fingerprint_body_mutations() {
let transport = sample_transport();
let context =
ProviderOutboundRequestContext::new("synthetic-memory-turn", 1_700_000_000_123)
.with_api_operation(aether_ai_formats::ApiOperation::OpenAiMemoriesSummarize);
let mut headers = BTreeMap::new();
let mut body = json!({"model":"gpt-6.1-sol","traces":[],"future":42});
let original = body.clone();
let result = apply_codex_fingerprint_convergence_policy(
&transport,
"openai:responses",
&context,
&mut headers,
&mut body,
);
assert_eq!(
result.reason,
ProviderOutboundRequestPolicyReason::NativeOperationExcluded
);
assert_eq!(body, original);
assert!(headers.is_empty());
}
#[test]
fn provider_config_switch_is_opt_in_and_codex_only() {
assert!(!codex_fingerprint_convergence_enabled("codex", None));
crates/aether-provider/transport/src/lib.rs
+1
View File
@@ -154,6 +154,7 @@ pub use rules::{
};
pub use same_format_provider::{
build_same_format_provider_headers, build_same_format_provider_request_body,
build_same_format_provider_request_body_for_operation,
build_same_format_provider_request_body_with_compatibility_report,
build_same_format_provider_request_body_with_compatibility_report_and_reasoning_replay_policy,
build_same_format_provider_upstream_url, classify_same_format_provider_request_behavior,
crates/aether-provider/transport/src/outbound_request_policy.rs
+12
View File
@@ -23,6 +23,7 @@ pub const PROVIDER_OUTBOUND_CONTEXT_MAX_VALUE_BYTES: usize = 256;
#[derive(Debug, Clone, PartialEq, Eq)]
pub struct ProviderOutboundRequestContext {
api_operation: Option<aether_ai_formats::ApiOperation>,
logical_turn_id: String,
original_turn_id: Option<String>,
original_client_session_id: Option<String>,
@@ -33,6 +34,7 @@ pub struct ProviderOutboundRequestContext {
impl ProviderOutboundRequestContext {
pub fn new(logical_turn_id: impl Into<String>, turn_started_at_unix_ms: u64) -> Self {
Self {
api_operation: None,
logical_turn_id: canonical_required_value(logical_turn_id.into(), "logical_turn_id"),
original_turn_id: None,
original_client_session_id: None,
@@ -68,6 +70,15 @@ impl ProviderOutboundRequestContext {
self.logical_turn_id.as_str()
}
pub fn with_api_operation(mut self, operation: aether_ai_formats::ApiOperation) -> Self {
self.api_operation = Some(operation);
self
}
pub fn api_operation(&self) -> Option<aether_ai_formats::ApiOperation> {
self.api_operation
}
pub fn original_turn_id(&self) -> Option<&str> {
self.original_turn_id.as_deref()
}
@@ -106,6 +117,7 @@ pub enum ProviderOutboundRequestPolicyReason {
AgentIdentityExcluded,
UnsupportedApiFormat,
CompactOperationExcluded,
NativeOperationExcluded,
Disabled,
RequestBodyNotObject,
}
crates/aether-provider/transport/src/provider_types.rs
+1 -1
View File
@@ -604,7 +604,7 @@ pub fn provider_type_admin_oauth_template(provider_type: &str) -> Option<Provide
authorize_url: "https://auth.openai.com/oauth/authorize",
token_url: "https://auth.openai.com/oauth/token",
client_id: "app_EMoamEEZ73f0CkXaXp7hrann",
scopes: &["openid", "email", "profile", "offline_access"],
scopes: aether_oauth::provider::providers::CODEX_OAUTH_SCOPES,
redirect_uri: "http://localhost:1455/auth/callback",
use_pkce: true,
}),
crates/aether-provider/transport/src/request_url/mod.rs
+112
View File
@@ -120,6 +120,43 @@ fn build_transport_request_url_inner(
return Some(url);
}
if params.api_operation == Some(ApiOperation::OpenAiMemoriesSummarize) {
if normalized_provider_api_format != "openai:responses" {
return None;
}
if let Some(path) = transport
.endpoint
.custom_path
.as_deref()
.map(str::trim)
.filter(|path| !path.is_empty())
{
// 显式操作模板也适用于原生同步操作。
if path.contains("{operation}") {
let path = expand_custom_path_template(path, build_path_params(params, false))?;
return build_passthrough_path_url(
&transport.endpoint.base_url,
&path,
params.request_query,
GATEWAY_CREDENTIAL_QUERY_KEYS,
);
}
// 仅描述 Responses 的自定义路径无法承接该操作。
return None;
}
// 以 Responses 的同一提供商根路径派生原生端点。
let mut url = Url::parse(&build_openai_responses_url(
&transport.endpoint.base_url,
strip_gateway_credential_query_parameters(params.request_query).as_deref(),
false,
))
.ok()?;
let root = url.path().strip_suffix("/responses")?;
let path = format!("{root}/memories/trace_summarize");
url.set_path(&path);
return Some(url.to_string());
}
let xai_base =
crate::xai::resolved_xai_upstream_base_url(transport, &normalized_provider_api_format);
let request_base_url = xai_base
@@ -558,6 +595,14 @@ pub fn transport_supports_api_operation(
provider_api_format: &str,
operation: Option<ApiOperation>,
) -> bool {
if operation == Some(ApiOperation::OpenAiMemoriesSummarize) {
return aether_ai_formats::normalize_api_format_alias(provider_api_format)
== "openai:responses"
&& !crate::kiro::is_kiro_provider_transport(transport)
&& !crate::grok::is_grok_provider_transport(transport)
&& !is_antigravity_provider_transport(transport)
&& !is_gemini_cli_provider_transport(transport);
}
if operation != Some(ApiOperation::ClaudeCountTokens) {
return true;
}
@@ -1221,6 +1266,73 @@ mod tests {
assert_eq!(url, "https://api.openai.example/v1/responses?tenant=demo");
}
#[test]
fn memories_url_respects_operation_templates_and_rejects_incompatible_paths() {
let params = TransportRequestUrlParams {
provider_api_format: "openai:responses",
mapped_model: Some("gpt-6.1-sol"),
upstream_is_stream: false,
request_query: Some("key=synthetic&tenant=demo"),
kiro_api_region: None,
api_operation: Some(ApiOperation::OpenAiMemoriesSummarize),
};
let transport = sample_transport(
"codex",
"openai:responses",
"https://example.com",
Some("/native/{operation}"),
);
assert_eq!(
build_transport_request_url(&transport, params).as_deref(),
Some("https://example.com/native/trace_summarize?tenant=demo")
);
let incompatible = sample_transport(
"codex",
"openai:responses",
"https://example.com",
Some("/native/responses"),
);
assert!(build_transport_request_url(&incompatible, params).is_none());
for provider in ["kiro", "grok", "antigravity", "gemini_cli"] {
let private =
sample_transport(provider, "openai:responses", "https://example.com", None);
assert!(
build_transport_request_url(&private, params).is_none(),
"{provider}"
);
}
}
#[test]
fn memories_url_uses_the_configured_provider_root_and_removes_gateway_auth() {
for (provider, base, expected) in [
(
"codex",
"https://chatgpt.com/backend-api/codex",
"https://chatgpt.com/backend-api/codex/memories/trace_summarize?tenant=demo",
),
(
"custom",
"https://example.com/v1",
"https://example.com/v1/memories/trace_summarize?tenant=demo",
),
] {
let transport = sample_transport(provider, "openai:responses", base, None);
let result = build_transport_request_url(
&transport,
TransportRequestUrlParams {
provider_api_format: "openai:responses",
mapped_model: Some("gpt-6.1-sol"),
upstream_is_stream: false,
request_query: Some("key=synthetic-secret&tenant=demo"),
kiro_api_region: None,
api_operation: Some(ApiOperation::OpenAiMemoriesSummarize),
},
);
assert_eq!(result.as_deref(), Some(expected));
}
}
#[test]
fn builds_openai_search_url_for_codex_provider_root() {
let transport = sample_transport(
crates/aether-provider/transport/src/same_format_provider/mod.rs
+71 -2
View File
@@ -273,7 +273,10 @@ pub fn classify_same_format_provider_request_behavior_for_operation(
);
let operation_requires_sync = matches!(
api_operation,
Some(aether_ai_formats::ApiOperation::ClaudeCountTokens)
Some(
aether_ai_formats::ApiOperation::ClaudeCountTokens
| aether_ai_formats::ApiOperation::OpenAiMemoriesSummarize
)
);
let upstream_is_stream = !operation_requires_sync
&& aether_ai_formats::resolve_upstream_is_stream_for_provider(
@@ -321,6 +324,7 @@ pub fn build_same_format_provider_request_body(
input,
None,
aether_ai_formats::OpenAiResponsesReasoningReplayPolicy::OpenAiItemIds,
false,
)
}
@@ -337,11 +341,34 @@ pub fn build_same_format_provider_request_body_with_compatibility_report_and_rea
input: SameFormatProviderRequestBodyInput<'_>,
reasoning_replay_policy: aether_ai_formats::OpenAiResponsesReasoningReplayPolicy,
) -> Option<SameFormatProviderRequestBodyOutput> {
build_same_format_provider_request_body_for_operation(input, reasoning_replay_policy, None)
}
pub fn build_same_format_provider_request_body_for_operation(
input: SameFormatProviderRequestBodyInput<'_>,
reasoning_replay_policy: aether_ai_formats::OpenAiResponsesReasoningReplayPolicy,
api_operation: Option<aether_ai_formats::ApiOperation>,
) -> Option<SameFormatProviderRequestBodyOutput> {
let native_memories =
api_operation == Some(aether_ai_formats::ApiOperation::OpenAiMemoriesSummarize);
if native_memories
&& (!aether_ai_formats::api_format_alias_matches(
input.provider_api_format,
"openai:responses",
) || !aether_ai_formats::api_format_alias_matches(
input.client_api_format,
"openai:responses",
) || input.kiro_auth_config.is_some()
|| input.is_claude_code)
{
return None;
}
let mut compatibility_edits = Vec::new();
let body = build_same_format_provider_request_body_inner(
input,
Some(&mut compatibility_edits),
reasoning_replay_policy,
native_memories,
)?;
Some(SameFormatProviderRequestBodyOutput {
body,
@@ -355,7 +382,10 @@ pub fn enforce_same_format_provider_api_operation_body_policy(
) -> bool {
if !matches!(
api_operation,
Some(aether_ai_formats::ApiOperation::ClaudeCountTokens)
Some(
aether_ai_formats::ApiOperation::ClaudeCountTokens
| aether_ai_formats::ApiOperation::OpenAiMemoriesSummarize
)
) {
return false;
}
@@ -367,6 +397,7 @@ fn build_same_format_provider_request_body_inner(
input: SameFormatProviderRequestBodyInput<'_>,
mut compatibility_edits: Option<&mut Vec<SameFormatProviderCompatibilityEdit>>,
reasoning_replay_policy: aether_ai_formats::OpenAiResponsesReasoningReplayPolicy,
native_memories: bool,
) -> Option<Value> {
if let Some(kiro_auth_config) = input.kiro_auth_config {
let body = build_kiro_provider_request_body(
@@ -523,6 +554,11 @@ fn build_same_format_provider_request_body_inner(
"applied configured provider body rules",
);
}
if native_memories {
// 记忆端点使用原生 JSON，不注入 Responses 的 input/store/include/stream，
// 也不通过 Responses 规则归一化 traces。
return Some(provider_request_body);
}
if matches!(input.family, SameFormatProviderFamily::Gemini)
&& aether_ai_formats::api_format_alias_matches(
input.provider_api_format,
@@ -992,6 +1028,39 @@ mod tests {
};
use serde_json::json;
#[test]
fn memories_preserves_native_traces_and_does_not_apply_responses_stream_policy() {
let body = json!({"model": "memory-global", "reasoning": {"effort": "high"},
"traces": [{"id": "synthetic-trace", "items": [{"future": 7}]}],
"future_request": {"opaque": [1, 2, 3]}});
let input = SameFormatProviderRequestBodyInput {
body_json: &body,
mapped_model: "memory-upstream",
client_api_format: "openai:responses",
provider_api_format: "openai:responses",
source_model: Some("memory-global"),
family: SameFormatProviderFamily::Standard,
body_rules: None,
request_headers: None,
upstream_is_stream: false,
force_body_stream_field: true,
kiro_auth_config: None,
is_claude_code: false,
enable_model_directives: false,
};
let result = build_same_format_provider_request_body_for_operation(
input,
aether_ai_formats::OpenAiResponsesReasoningReplayPolicy::OpenAiItemIds,
Some(aether_ai_formats::ApiOperation::OpenAiMemoriesSummarize),
)
.unwrap();
let mut expected = body.clone();
expected["model"] = json!("memory-upstream");
assert_eq!(result.body, expected);
assert!(result.body.get("input").is_none());
assert!(result.body.get("stream").is_none());
}
fn sample_transport(provider_type: &str) -> GatewayProviderTransportSnapshot {
GatewayProviderTransportSnapshot {
provider: GatewayProviderTransportProvider {
crates/aether-usage/runtime/src/report.rs
+2
View File
@@ -299,6 +299,7 @@ pub fn is_local_ai_sync_report_kind(report_kind: &str) -> bool {
| "claude_chat_sync_error"
| "gemini_chat_sync_error"
| "openai_responses_sync_success"
| "openai_memories_sync_success"
| "openai_responses_compact_sync_success"
| "openai_responses_sync_error"
| "openai_responses_compact_sync_error"
@@ -946,6 +947,7 @@ mod tests {
));
assert!(is_local_ai_sync_report_kind("openai_image_sync_success"));
assert!(is_local_ai_sync_report_kind("openai_search_sync_success"));
assert!(is_local_ai_sync_report_kind("openai_memories_sync_success"));
assert!(is_local_ai_sync_report_kind("openai_image_sync_error"));
assert!(is_local_ai_sync_report_kind(
"openai_embedding_sync_success"
docs/operations/codex-cli-alignment.md
+43
View File
@@ -0,0 +1,43 @@
# Codex CLI 通用协议对齐
本次对齐以官方 `openai/codex` 稳定标签 `rust-v0.159.3` 为可发布版本依据，同时核查最新 `main` 的协议实现。稳定标签提交为 `01fc69f4026735edfdf6789820549727a4867b11`，核查的 main 提交为 `444da310e108da16aaeb18fd790b0ac464f08aca`。
网关承接的是客户端与上游之间的协议，不复制 CLI 的本地工具执行、终端界面或个人账户状态。
| 对象 | 当前行为 |
| --- | --- |
| 客户端画像 | 默认版本更新为 0.159.3，现有后台 npm 稳定版本刷新继续生效；UA 按官方格式使用网关公开 OS、版本和架构，无终端时采用官方 `unknown` 标识 |
| OAuth | Codex 模板共享六项官方 scope，包含连接器读取及调用权限，并携带 `originator=codex_cli_rs`；其他 OAuth 类型保持独立模板 |
| 模型目录发现 | UA 与查询参数 `client_version` 使用同一版本；拒绝非法版本，保留现有保护头和运行时账户鉴权 |
| 模型能力 | 从官方公开模型目录提取能力快照，涵盖 `gpt-6-astra`、`gpt-6.1-sol`、六档推理强度及其他模型；账户返回的模型目录继续优先 |
| WebSocket 元数据 | 仅公开模型目录 ETag、轮次状态、实际模型与安全缓冲头；保留公开事件及未知公开字段、事件顺序 |
| 上游账户配额 | `codex.rate_limits` 继续进入账户级熔断与持久化路径，不当作网关用户自己的配额公开 |
| 原生记忆接口 | `POST /v1/memories/trace_summarize` 复用 Responses 权限及调度，执行原生同步操作，保留 traces、output 数组和未来字段，不注入 Responses 的 input/store/include 或流式默认值 |
公开快照来源为 `codex-rs/models-manager/models.json`。未复制提示词或账户套餐可见性；保留官方公开的 `comp_hash` 压缩兼容性标记，以支持 CLI Guardian 的压缩上下文复用；没有引入个人用户标识、已有会话 UUID、Cookie、访问令牌或账户凭据。运行时鉴权和账户字段仍由提供商密钥配置产生。
新增模型能力快照不等于授权访问该模型。可用模型应通过正式管理界面的上游模型查询、全局模型和提供商模型配置，以及密钥模型限制来设置。远端目录及实际账户权限决定上游是否支持模型，不能通过修改 `/models` 列表绕过。
六档推理强度描述 CLI 的选择项。`ultra` 是 CLI 的本地多代理模式：官方 `ModelInfo::resolve_reasoning_effort` 会把普通推理请求转换为有效的 `multi_agent_reasoning_effort`，否则依次采用 `max`、最高非 `ultra` 档位或 `medium`；本地模式仍保持 `ultra`。网关保留模型卡片的相关公开能力，由 CLI 完成该转换，不在原始 Responses 请求中擅自把 `ultra` 等同于 `max`，也不实现客户端的多代理编排。直接发送 `reasoning.effort=ultra` 与 CLI 选择 `ultra` 的请求不同，上游可能拒绝前者。
现场使用校验过发行资产摘要的官方 `0.159.3` CLI，分别对 `gpt-6-astra` 和 `gpt-6.1-sol` 选择 `ultra`，均成功完成；网关使用记录确认请求档位为模型指定的 `xhigh`。两模型的原始 Responses `low`、`medium`、`high`、`xhigh`、`max` 调用也均完成。直接发送原始 `ultra` 时，现场上游候选返回 HTTP 400，按现有重试策略最终返回 503；该结果不作为 CLI 的 `ultra` 模式验收失败。
同一现场的 WebSocket 验收对两模型分别完成两轮 `generate=false` 预热和 `previous_response_id` 续接，接收到了公开完成事件与 Codex metadata；这项检查覆盖连接、元数据和续接，不等同于完整生成、工具调用或所有重连场景。验证使用正式提供商开关，完成后恢复原配置。
记忆接口是 CLI 可选功能对应的协议。是否启动记忆任务仍由 CLI 自己的 feature/config 决定。它要求提供商支持该原生端点；Kiro、Grok、Antigravity 和 Gemini CLI 等私有适配器不能通过格式标签冒充支持。配置自定义路径时须使用 `/memories/{operation}` 等模板；仅描述 Responses 的固定路径会被拒绝。
Apps 文件上传属于 CLI 的 ChatGPT Apps 专用路径，普通自定义 API 提供商不会启动该流程；本次不将其伪装成通用 Responses 路由。`aether-vscodex` 的 app-server UI 协议版本属于独立客户端，不覆盖成 CLI 版本。
验证命令：
```bash
cargo fmt --all -- --check
RUST_MIN_STACK=16777216 cargo test --locked -p aether-ai-formats -p aether-oauth -p aether-model-fetch -p aether-provider-transport -p aether-usage-runtime --lib -- --test-threads=1
RUST_MIN_STACK=16777216 cargo test --locked -p aether-gateway --lib -- --test-threads=1
RUST_MIN_STACK=16777216 cargo test --locked -p aether-gateway --bins
RUST_MIN_STACK=16777216 cargo test --locked -p aether-gateway --test admin_unsigned_identity_headers --test architecture_guard
```
完整网关测试需要可执行的临时 PostgreSQL 工具（`AETHER_INITDB_BIN`、`AETHER_POSTGRES_BIN`、`AETHER_PG_CTL_BIN`）、权限受控的临时目录，以及不允许组写入的测试运行目录。Unix socket、更新元数据与私有运行文件测试会主动拒绝不安全的路径；测试目录应以 `umask 022` 或更严格的权限创建。
原生记忆端到端测试覆盖真实网关的权限、候选调度、执行计划、模型指令、原生 JSON、成功候选状态与明确停止重试策略下的上游错误响应；执行端使用本地测试服务器，实际账户网络可用性须在部署现场单独验证。