Add auth env observability (#14905)

CXC-410 Emit Env Var Status with `/feedback` report

Add more observability on top of #14611 

[Unset](https://openai.sentry.io/issues/7340419168/?project=4510195390611458&query=019cfa8d-c1ba-7002-96fa-e35fc340551d&referrer=issue-stream)

[Set](https://openai.sentry.io/issues/7340426331/?project=4510195390611458&query=019cfa91-aba1-7823-ab7e-762edfbc0ed4&referrer=issue-stream)
<img width="1063" height="610" alt="image"
src="https://github.com/user-attachments/assets/937ab026-1c2d-4757-81d5-5f31b853113e"
/>


###### Summary
- Adds auth-env telemetry that records whether key auth-related env
overrides were present on session start and request paths.
- Threads those auth-env fields through `/responses`, websocket, and
`/models` telemetry and feedback metadata.
- Buckets custom provider `env_key` configuration to a safe
`"configured"` value instead of emitting raw config text.
- Keeps the slice observability-only: no raw token values or raw URLs
are emitted.

###### Rationale (from spec findings)
- 401 and auth-path debugging needs a way to distinguish env-driven auth
paths from sessions with no auth env override.
- Startup and model-refresh failures need the same auth-env diagnostics
as normal request failures.
- Feedback and Sentry tags need the same auth-env signal as OTel events
so reports can be triaged consistently.
- Custom provider config is user-controlled text, so the telemetry
contract must stay presence-only / bucketed.

###### Scope
- Adds a small `AuthEnvTelemetry` bundle for env presence collection and
threads it through the main request/session telemetry paths.
- Does not add endpoint/base-url/provider-header/geo routing attribution
or broader telemetry API redesign.

###### Trade-offs
- `provider_env_key_name` is bucketed to `"configured"` instead of
preserving the literal configured env var name.
- `/models` is included because startup/model-refresh auth failures need
the same diagnostics, but broader parity work remains out of scope.
- This slice keeps the existing telemetry APIs and layers auth-env
fields onto them rather than redesigning the metadata model.

###### Client follow-up
- Add the separate endpoint/base-url attribution slice if routing-source
diagnosis is still needed.
- Add provider-header or residency attribution only if auth-env presence
proves insufficient in real reports.
- Revisit whether any additional auth-related env inputs need safe
bucketing after more 401 triage data.

###### Testing
- `cargo test -p codex-core emit_feedback_request_tags -- --nocapture`
- `cargo test -p codex-core
collect_auth_env_telemetry_buckets_provider_env_key_name -- --nocapture`
- `cargo test -p codex-core
models_request_telemetry_emits_auth_env_feedback_tags_on_failure --
--nocapture`
- `cargo test -p codex-otel
otel_export_routing_policy_routes_api_request_auth_observability --
--nocapture`
- `cargo test -p codex-otel
otel_export_routing_policy_routes_websocket_connect_auth_observability
-- --nocapture`
- `cargo test -p codex-otel
otel_export_routing_policy_routes_websocket_request_transport_observability
-- --nocapture`
- `cargo test -p codex-core --no-run --message-format short`
- `cargo test -p codex-otel --no-run --message-format short`

---------

Co-authored-by: Codex <noreply@openai.com>
This commit is contained in:
Colin YoungandCodex authored and GitHub committed 2026-03-17 14:26:27 -07:00
1 parent ee756eb80f
commit 0d2ff40a58
12 files changed
+770 -161

No files matched your search

+40 -17
View File
@@ -4,6 +4,8 @@ use crate::api_bridge::map_api_error;
use crate::auth::AuthManager;
use crate::auth::AuthMode;
use crate::auth::CodexAuth;
use crate::auth_env_telemetry::AuthEnvTelemetry;
use crate::auth_env_telemetry::collect_auth_env_telemetry;
use crate::config::Config;
use crate::default_client::build_reqwest_client;
use crate::error::CodexErr;
@@ -15,7 +17,7 @@ use crate::models_manager::model_info;
use crate::response_debug_context::extract_response_debug_context;
use crate::response_debug_context::telemetry_transport_error_message;
use crate::util::FeedbackRequestTags;
use crate::util::emit_feedback_request_tags;
use crate::util::emit_feedback_request_tags_with_auth_env;
use codex_api::ModelsClient;
use codex_api::RequestTelemetry;
use codex_api::ReqwestTransport;
@@ -46,6 +48,7 @@ struct ModelsRequestTelemetry {
auth_mode: Option<String>,
auth_header_attached: bool,
auth_header_name: Option<&'static str>,
auth_env: AuthEnvTelemetry,
}
impl RequestTelemetry for ModelsRequestTelemetry {
@@ -74,6 +77,12 @@ impl RequestTelemetry for ModelsRequestTelemetry {
endpoint = MODELS_ENDPOINT,
auth.header_attached = self.auth_header_attached,
auth.header_name = self.auth_header_name,
auth.env_openai_api_key_present = self.auth_env.openai_api_key_env_present,
auth.env_codex_api_key_present = self.auth_env.codex_api_key_env_present,
auth.env_codex_api_key_enabled = self.auth_env.codex_api_key_env_enabled,
auth.env_provider_key_name = self.auth_env.provider_env_key_name.as_deref(),
auth.env_provider_key_present = self.auth_env.provider_env_key_present,
auth.env_refresh_token_url_override_present = self.auth_env.refresh_token_url_override_present,
auth.request_id = response_debug.request_id.as_deref(),
auth.cf_ray = response_debug.cf_ray.as_deref(),
auth.error = response_debug.auth_error.as_deref(),
@@ -92,28 +101,37 @@ impl RequestTelemetry for ModelsRequestTelemetry {
endpoint = MODELS_ENDPOINT,
auth.header_attached = self.auth_header_attached,
auth.header_name = self.auth_header_name,
auth.env_openai_api_key_present = self.auth_env.openai_api_key_env_present,
auth.env_codex_api_key_present = self.auth_env.codex_api_key_env_present,
auth.env_codex_api_key_enabled = self.auth_env.codex_api_key_env_enabled,
auth.env_provider_key_name = self.auth_env.provider_env_key_name.as_deref(),
auth.env_provider_key_present = self.auth_env.provider_env_key_present,
auth.env_refresh_token_url_override_present = self.auth_env.refresh_token_url_override_present,
auth.request_id = response_debug.request_id.as_deref(),
auth.cf_ray = response_debug.cf_ray.as_deref(),
auth.error = response_debug.auth_error.as_deref(),
auth.error_code = response_debug.auth_error_code.as_deref(),
auth.mode = self.auth_mode.as_deref(),
);
emit_feedback_request_tags(&FeedbackRequestTags {
endpoint: MODELS_ENDPOINT,
auth_header_attached: self.auth_header_attached,
auth_header_name: self.auth_header_name,
auth_mode: self.auth_mode.as_deref(),
auth_retry_after_unauthorized: None,
auth_recovery_mode: None,
auth_recovery_phase: None,
auth_connection_reused: None,
auth_request_id: response_debug.request_id.as_deref(),
auth_cf_ray: response_debug.cf_ray.as_deref(),
auth_error: response_debug.auth_error.as_deref(),
auth_error_code: response_debug.auth_error_code.as_deref(),
auth_recovery_followup_success: None,
auth_recovery_followup_status: None,
});
emit_feedback_request_tags_with_auth_env(
&FeedbackRequestTags {
endpoint: MODELS_ENDPOINT,
auth_header_attached: self.auth_header_attached,
auth_header_name: self.auth_header_name,
auth_mode: self.auth_mode.as_deref(),
auth_retry_after_unauthorized: None,
auth_recovery_mode: None,
auth_recovery_phase: None,
auth_connection_reused: None,
auth_request_id: response_debug.request_id.as_deref(),
auth_cf_ray: response_debug.cf_ray.as_deref(),
auth_error: response_debug.auth_error.as_deref(),
auth_error_code: response_debug.auth_error_code.as_deref(),
auth_recovery_followup_success: None,
auth_recovery_followup_status: None,
},
&self.auth_env,
);
}
}
@@ -417,11 +435,16 @@ impl ModelsManager {
let auth_mode = auth.as_ref().map(CodexAuth::auth_mode);
let api_provider = self.provider.to_api_provider(auth_mode)?;
let api_auth = auth_provider_from_auth(auth.clone(), &self.provider)?;
let auth_env = collect_auth_env_telemetry(
&self.provider,
self.auth_manager.codex_api_key_env_enabled(),
);
let transport = ReqwestTransport::new(build_reqwest_client());
let request_telemetry: Arc<dyn RequestTelemetry> = Arc::new(ModelsRequestTelemetry {
auth_mode: auth_mode.map(|mode| TelemetryAuthMode::from(mode).to_string()),
auth_header_attached: api_auth.auth_header_attached(),
auth_header_name: api_auth.auth_header_name(),
auth_env,
});
let client = ModelsClient::new(transport, api_provider, api_auth)
.with_telemetry(Some(request_telemetry));