Files
codex/codex-rs/core/tests/suite/personality.rs
Michael Bolin bfff0c729f config: enforce enterprise feature requirements (#13388)
## Why

Enterprises can already constrain approvals, sandboxing, and web search
through `requirements.toml` and MDM, but feature flags were still only
configurable as managed defaults. That meant an enterprise could suggest
feature values, but it could not actually pin them.

This change closes that gap and makes enterprise feature requirements
behave like the other constrained settings. The effective feature set
now stays consistent with enterprise requirements during config load,
when config writes are validated, and when runtime code mutates feature
flags later in the session.

It also tightens the runtime API for managed features. `ManagedFeatures`
now follows the same constraint-oriented shape as `Constrained<T>`
instead of exposing panic-prone mutation helpers, and production code
can no longer construct it through an unconstrained `From<Features>`
path.

The PR also hardens the `compact_resume_fork` integration coverage on
Windows. After the feature-management changes,
`compact_resume_after_second_compaction_preserves_history` was
overflowing the libtest/Tokio thread stacks on Windows, so the test now
uses an explicit larger-stack harness as a pragmatic mitigation. That
may not be the ideal root-cause fix, and it merits a parallel
investigation into whether part of the async future chain should be
boxed to reduce stack pressure instead.

## What Changed

Enterprises can now pin feature values in `requirements.toml` with the
requirements-side `features` table:

```toml
[features]
personality = true
unified_exec = false
```

Only canonical feature keys are allowed in the requirements `features`
table; omitted keys remain unconstrained.

- Added a requirements-side pinned feature map to
`ConfigRequirementsToml`, threaded it through source-preserving
requirements merge and normalization in `codex-config`, and made the
TOML surface use `[features]` (while still accepting legacy
`[feature_requirements]` for compatibility).
- Exposed `featureRequirements` from `configRequirements/read`,
regenerated the JSON/TypeScript schema artifacts, and updated the
app-server README.
- Wrapped the effective feature set in `ManagedFeatures`, backed by
`ConstrainedWithSource<Features>`, and changed its API to mirror
`Constrained<T>`: `can_set(...)`, `set(...) -> ConstraintResult<()>`,
and result-returning `enable` / `disable` / `set_enabled` helpers.
- Removed the legacy-usage and bulk-map passthroughs from
`ManagedFeatures`; callers that need those behaviors now mutate a plain
`Features` value and reapply it through `set(...)`, so the constrained
wrapper remains the enforcement boundary.
- Removed the production loophole for constructing unconstrained
`ManagedFeatures`. Non-test code now creates it through the configured
feature-loading path, and `impl From<Features> for ManagedFeatures` is
restricted to `#[cfg(test)]`.
- Rejected legacy feature aliases in enterprise feature requirements,
and return a load error when a pinned combination cannot survive
dependency normalization.
- Validated config writes against enterprise feature requirements before
persisting changes, including explicit conflicting writes and
profile-specific feature states that normalize into invalid
combinations.
- Updated runtime and TUI feature-toggle paths to use the constrained
setter API and to persist or apply the effective post-constraint value
rather than the requested value.
- Updated the `core_test_support` Bazel target to include the bundled
core model-catalog fixtures in its runtime data, so helper code that
resolves `core/models.json` through runfiles works in remote Bazel test
environments.
- Renamed the core config test coverage to emphasize that effective
feature values are normalized at runtime, while conflicting persisted
config writes are rejected.
- Ran `compact_resume_after_second_compaction_preserves_history` inside
an explicit 8 MiB test thread and Tokio runtime worker stack, following
the existing larger-stack integration-test pattern, to keep the Windows
`compact_resume_fork` test slice from aborting while a parallel
investigation continues into whether some of the underlying async
futures should be boxed.

## Verification

- `cargo test -p codex-config`
- `cargo test -p codex-core feature_requirements_ -- --nocapture`
- `cargo test -p codex-core
load_requirements_toml_produces_expected_constraints -- --nocapture`
- `cargo test -p codex-core
compact_resume_after_second_compaction_preserves_history -- --nocapture`
- `cargo test -p codex-core compact_resume_fork -- --nocapture`
- Re-ran the built `codex-core` `tests/all` binary with
`RUST_MIN_STACK=262144` for
`compact_resume_after_second_compaction_preserves_history` to confirm
the explicit-stack harness fixes the deterministic low-stack repro.
- `cargo test -p codex-core`
- This still fails locally in unrelated integration areas that expect
the `codex` / `test_stdio_server` binaries or hit existing `search_tool`
wiremock mismatches.

## Docs

`developers.openai.com/codex` should document the requirements-side
`[features]` table for enterprise and MDM-managed configuration,
including that it only accepts canonical feature keys and that
conflicting config writes are rejected.
2026-03-04 04:40:22 +00:00

896 lines
32 KiB
Rust

use codex_core::config::types::Personality;
use codex_core::features::Feature;
use codex_core::models_manager::manager::ModelsManager;
use codex_core::models_manager::manager::RefreshStrategy;
use codex_protocol::config_types::ReasoningSummary;
use codex_protocol::openai_models::ConfigShellToolType;
use codex_protocol::openai_models::ModelInfo;
use codex_protocol::openai_models::ModelInstructionsVariables;
use codex_protocol::openai_models::ModelMessages;
use codex_protocol::openai_models::ModelVisibility;
use codex_protocol::openai_models::ModelsResponse;
use codex_protocol::openai_models::ReasoningEffort;
use codex_protocol::openai_models::ReasoningEffortPreset;
use codex_protocol::openai_models::TruncationPolicyConfig;
use codex_protocol::openai_models::default_input_modalities;
use codex_protocol::protocol::AskForApproval;
use codex_protocol::protocol::EventMsg;
use codex_protocol::protocol::Op;
use codex_protocol::protocol::SandboxPolicy;
use codex_protocol::user_input::UserInput;
use core_test_support::load_default_config_for_test;
use core_test_support::responses::mount_models_once;
use core_test_support::responses::mount_sse_once;
use core_test_support::responses::mount_sse_sequence;
use core_test_support::responses::sse_completed;
use core_test_support::responses::start_mock_server;
use core_test_support::skip_if_no_network;
use core_test_support::test_codex::test_codex;
use core_test_support::wait_for_event;
use pretty_assertions::assert_eq;
use std::sync::Arc;
use tempfile::TempDir;
use tokio::time::Duration;
use tokio::time::Instant;
use tokio::time::sleep;
use wiremock::BodyPrintLimit;
use wiremock::MockServer;
const LOCAL_FRIENDLY_TEMPLATE: &str =
"You optimize for team morale and being a supportive teammate as much as code quality.";
const LOCAL_PRAGMATIC_TEMPLATE: &str = "You are a deeply pragmatic, effective software engineer.";
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn personality_does_not_mutate_base_instructions_without_template() {
let codex_home = TempDir::new().expect("create temp dir");
let mut config = load_default_config_for_test(&codex_home).await;
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
config.personality = Some(Personality::Friendly);
let model_info = codex_core::test_support::construct_model_info_offline("gpt-5.1", &config);
assert_eq!(
model_info.get_model_instructions(config.personality),
model_info.base_instructions
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn base_instructions_override_disables_personality_template() {
let codex_home = TempDir::new().expect("create temp dir");
let mut config = load_default_config_for_test(&codex_home).await;
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
config.personality = Some(Personality::Friendly);
config.base_instructions = Some("override instructions".to_string());
let model_info =
codex_core::test_support::construct_model_info_offline("gpt-5.2-codex", &config);
assert_eq!(model_info.base_instructions, "override instructions");
assert_eq!(
model_info.get_model_instructions(config.personality),
"override instructions"
);
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn user_turn_personality_none_does_not_add_update_message() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
let mut builder = test_codex()
.with_model("gpt-5.2-codex")
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let request = resp_mock.single_request();
let developer_texts = request.message_input_texts("developer");
assert!(
!developer_texts
.iter()
.any(|text| text.contains("<personality_spec>")),
"did not expect a personality update message when personality is None"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn config_personality_some_sets_instructions_template() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
let mut builder = test_codex()
.with_model("gpt-5.2-codex")
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
config.personality = Some(Personality::Friendly);
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let request = resp_mock.single_request();
let instructions_text = request.instructions_text();
assert!(
instructions_text.contains(LOCAL_FRIENDLY_TEMPLATE),
"expected personality update to include the local friendly template, got: {instructions_text:?}"
);
let developer_texts = request.message_input_texts("developer");
for text in developer_texts {
assert!(
!text.contains("<personality_spec>"),
"expected no personality update message in developer input"
);
}
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn config_personality_none_sends_no_personality() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
let mut builder = test_codex()
.with_model("gpt-5.2-codex")
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
config.personality = Some(Personality::None);
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let request = resp_mock.single_request();
let instructions_text = request.instructions_text();
assert!(
!instructions_text.contains(LOCAL_FRIENDLY_TEMPLATE),
"expected no friendly personality template, got: {instructions_text:?}"
);
assert!(
!instructions_text.contains(LOCAL_PRAGMATIC_TEMPLATE),
"expected no pragmatic personality template, got: {instructions_text:?}"
);
assert!(
!instructions_text.contains("{{ personality }}"),
"expected personality placeholder to be removed, got: {instructions_text:?}"
);
let developer_texts = request.message_input_texts("developer");
assert!(
!developer_texts
.iter()
.any(|text| text.contains("<personality_spec>")),
"did not expect a personality update message when personality is None"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn default_personality_is_pragmatic_without_config_toml() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
let mut builder = test_codex()
.with_model("gpt-5.2-codex")
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let request = resp_mock.single_request();
let instructions_text = request.instructions_text();
assert!(
instructions_text.contains(LOCAL_PRAGMATIC_TEMPLATE),
"expected default friendly template, got: {instructions_text:?}"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn user_turn_personality_some_adds_update_message() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let resp_mock = mount_sse_sequence(
&server,
vec![sse_completed("resp-1"), sse_completed("resp-2")],
)
.await;
let mut builder = test_codex()
.with_model("exp-codex-personality")
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
test.codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: None,
sandbox_policy: None,
windows_sandbox_level: None,
model: None,
effort: None,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: Some(Personality::Friendly),
})
.await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let requests = resp_mock.requests();
assert_eq!(requests.len(), 2, "expected two requests");
let request = requests
.last()
.expect("expected personality update request");
let developer_texts = request.message_input_texts("developer");
let personality_text = developer_texts
.iter()
.find(|text| text.contains("<personality_spec>"))
.expect("expected personality update message in developer input");
assert!(
personality_text.contains("The user has requested a new communication style."),
"expected personality update preamble, got {personality_text:?}"
);
assert!(
personality_text.contains(LOCAL_FRIENDLY_TEMPLATE),
"expected personality update to include the local pragmatic template, got: {personality_text:?}"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn user_turn_personality_same_value_does_not_add_update_message() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let resp_mock = mount_sse_sequence(
&server,
vec![sse_completed("resp-1"), sse_completed("resp-2")],
)
.await;
let mut builder = test_codex()
.with_model("exp-codex-personality")
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
config.personality = Some(Personality::Pragmatic);
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
test.codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: None,
sandbox_policy: None,
windows_sandbox_level: None,
model: None,
effort: None,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: Some(Personality::Pragmatic),
})
.await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let requests = resp_mock.requests();
assert_eq!(requests.len(), 2, "expected two requests");
let request = requests
.last()
.expect("expected second request after personality override");
let developer_texts = request.message_input_texts("developer");
let personality_text = developer_texts
.iter()
.find(|text| text.contains("<personality_spec>"));
assert!(
personality_text.is_none(),
"expected no personality preamble for unchanged personality, got {personality_text:?}"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn instructions_uses_base_if_feature_disabled() -> anyhow::Result<()> {
let codex_home = TempDir::new().expect("create temp dir");
let mut config = load_default_config_for_test(&codex_home).await;
config
.features
.disable(Feature::Personality)
.expect("test config should allow feature update");
config.personality = Some(Personality::Friendly);
let model_info =
codex_core::test_support::construct_model_info_offline("gpt-5.2-codex", &config);
assert_eq!(
model_info.get_model_instructions(config.personality),
model_info.base_instructions
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn user_turn_personality_skips_if_feature_disabled() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = start_mock_server().await;
let resp_mock = mount_sse_sequence(
&server,
vec![sse_completed("resp-1"), sse_completed("resp-2")],
)
.await;
let mut builder = test_codex()
.with_model("exp-codex-personality")
.with_config(|config| {
config
.features
.disable(Feature::Personality)
.expect("test config should allow feature update");
});
let test = builder.build(&server).await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
test.codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: None,
sandbox_policy: None,
windows_sandbox_level: None,
model: None,
effort: None,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: Some(Personality::Pragmatic),
})
.await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: test.config.permissions.approval_policy.value(),
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: test.session_configured.model.clone(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let requests = resp_mock.requests();
assert_eq!(requests.len(), 2, "expected two requests");
let request = requests
.last()
.expect("expected personality update request");
let developer_texts = request.message_input_texts("developer");
let personality_text = developer_texts
.iter()
.find(|text| text.contains("<personality_spec>"));
assert!(
personality_text.is_none(),
"expected no personality preamble, got {personality_text:?}"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn remote_model_friendly_personality_instructions_with_feature() -> anyhow::Result<()> {
skip_if_no_network!(Ok(()));
let server = MockServer::builder()
.body_print_limit(BodyPrintLimit::Limited(80_000))
.start()
.await;
let remote_slug = "codex-remote-default-personality";
let default_personality_message = "Default from remote template";
let friendly_personality_message = "Friendly variant";
let remote_model = ModelInfo {
slug: remote_slug.to_string(),
display_name: "Remote default personality test".to_string(),
description: Some("Remote model with default personality template".to_string()),
default_reasoning_level: Some(ReasoningEffort::Medium),
supported_reasoning_levels: vec![ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: ReasoningEffort::Medium.to_string(),
}],
shell_type: ConfigShellToolType::UnifiedExec,
visibility: ModelVisibility::List,
supported_in_api: true,
priority: 1,
upgrade: None,
base_instructions: "base instructions".to_string(),
model_messages: Some(ModelMessages {
instructions_template: Some("Base instructions\n{{ personality }}\n".to_string()),
instructions_variables: Some(ModelInstructionsVariables {
personality_default: Some(default_personality_message.to_string()),
personality_friendly: Some(friendly_personality_message.to_string()),
personality_pragmatic: Some("Pragmatic variant".to_string()),
}),
}),
supports_reasoning_summaries: false,
default_reasoning_summary: ReasoningSummary::Auto,
support_verbosity: false,
default_verbosity: None,
availability_nux: None,
apply_patch_tool_type: None,
truncation_policy: TruncationPolicyConfig::bytes(10_000),
supports_parallel_tool_calls: false,
supports_image_detail_original: false,
context_window: Some(128_000),
auto_compact_token_limit: None,
effective_context_window_percent: 95,
experimental_supported_tools: Vec::new(),
input_modalities: default_input_modalities(),
prefer_websockets: false,
used_fallback_model_metadata: false,
};
let _models_mock = mount_models_once(
&server,
ModelsResponse {
models: vec![remote_model],
},
)
.await;
let resp_mock = mount_sse_once(&server, sse_completed("resp-1")).await;
let mut builder = test_codex()
.with_auth(codex_core::CodexAuth::create_dummy_chatgpt_auth_for_testing())
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
config.model = Some(remote_slug.to_string());
config.personality = Some(Personality::Friendly);
});
let test = builder.build(&server).await?;
wait_for_model_available(&test.thread_manager.get_models_manager(), remote_slug).await;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: AskForApproval::Never,
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: remote_slug.to_string(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: Some(Personality::Friendly),
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let request = resp_mock.single_request();
let instructions_text = request.instructions_text();
assert!(
instructions_text.contains(friendly_personality_message),
"expected instructions to include the remote friendly personality template, got: {instructions_text:?}"
);
assert!(
!instructions_text.contains(default_personality_message),
"expected instructions to skip the remote default personality template, got: {instructions_text:?}"
);
Ok(())
}
#[tokio::test(flavor = "multi_thread", worker_threads = 2)]
async fn user_turn_personality_remote_model_template_includes_update_message() -> anyhow::Result<()>
{
skip_if_no_network!(Ok(()));
let server = MockServer::builder()
.body_print_limit(BodyPrintLimit::Limited(80_000))
.start()
.await;
let remote_slug = "codex-remote-personality";
let remote_friendly_message = "Friendly from remote template";
let remote_pragmatic_message = "Pragmatic from remote template";
let remote_model = ModelInfo {
slug: remote_slug.to_string(),
display_name: "Remote personality test".to_string(),
description: Some("Remote model with personality template".to_string()),
default_reasoning_level: Some(ReasoningEffort::Medium),
supported_reasoning_levels: vec![ReasoningEffortPreset {
effort: ReasoningEffort::Medium,
description: ReasoningEffort::Medium.to_string(),
}],
shell_type: ConfigShellToolType::UnifiedExec,
visibility: ModelVisibility::List,
supported_in_api: true,
priority: 1,
upgrade: None,
base_instructions: "base instructions".to_string(),
model_messages: Some(ModelMessages {
instructions_template: Some("Base instructions\n{{ personality }}\n".to_string()),
instructions_variables: Some(ModelInstructionsVariables {
personality_default: None,
personality_friendly: Some(remote_friendly_message.to_string()),
personality_pragmatic: Some(remote_pragmatic_message.to_string()),
}),
}),
supports_reasoning_summaries: false,
default_reasoning_summary: ReasoningSummary::Auto,
support_verbosity: false,
default_verbosity: None,
availability_nux: None,
apply_patch_tool_type: None,
truncation_policy: TruncationPolicyConfig::bytes(10_000),
supports_parallel_tool_calls: false,
supports_image_detail_original: false,
context_window: Some(128_000),
auto_compact_token_limit: None,
effective_context_window_percent: 95,
experimental_supported_tools: Vec::new(),
input_modalities: default_input_modalities(),
prefer_websockets: false,
used_fallback_model_metadata: false,
};
let _models_mock = mount_models_once(
&server,
ModelsResponse {
models: vec![remote_model],
},
)
.await;
let resp_mock = mount_sse_sequence(
&server,
vec![sse_completed("resp-1"), sse_completed("resp-2")],
)
.await;
let mut builder = test_codex()
.with_auth(codex_core::CodexAuth::create_dummy_chatgpt_auth_for_testing())
.with_config(|config| {
config
.features
.enable(Feature::Personality)
.expect("test config should allow feature update");
config.model = Some("gpt-5.2-codex".to_string());
});
let test = builder.build(&server).await?;
wait_for_model_available(&test.thread_manager.get_models_manager(), remote_slug).await;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: AskForApproval::Never,
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: remote_slug.to_string(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
test.codex
.submit(Op::OverrideTurnContext {
cwd: None,
approval_policy: None,
sandbox_policy: None,
windows_sandbox_level: None,
model: None,
effort: None,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: Some(Personality::Friendly),
})
.await?;
test.codex
.submit(Op::UserTurn {
items: vec![UserInput::Text {
text: "hello".into(),
text_elements: Vec::new(),
}],
final_output_json_schema: None,
cwd: test.cwd_path().to_path_buf(),
approval_policy: AskForApproval::Never,
sandbox_policy: SandboxPolicy::new_read_only_policy(),
model: remote_slug.to_string(),
effort: test.config.model_reasoning_effort,
summary: None,
service_tier: None,
collaboration_mode: None,
personality: None,
})
.await?;
wait_for_event(&test.codex, |ev| matches!(ev, EventMsg::TurnComplete(_))).await;
let requests = resp_mock.requests();
assert_eq!(requests.len(), 2, "expected two requests");
let request = requests
.last()
.expect("expected personality update request");
let developer_texts = request.message_input_texts("developer");
let personality_text = developer_texts
.iter()
.find(|text| text.contains("<personality_spec>"))
.expect("expected personality update message in developer input");
assert!(
personality_text.contains("The user has requested a new communication style."),
"expected personality update preamble, got {personality_text:?}"
);
assert!(
personality_text.contains(remote_friendly_message),
"expected personality update to include remote template, got: {personality_text:?}"
);
Ok(())
}
async fn wait_for_model_available(manager: &Arc<ModelsManager>, slug: &str) {
let deadline = Instant::now() + Duration::from_secs(2);
loop {
let models = manager.list_models(RefreshStrategy::OnlineIfUncached).await;
if models.iter().any(|model| model.model == slug) {
return;
}
if Instant::now() >= deadline {
panic!("timed out waiting for the remote model {slug} to appear");
}
sleep(Duration::from_millis(25)).await;
}
}