Fix OpenAI connector health check configuration

[matdev83]

Summary

• ensure the OpenAI connector reads the dedicated disable_health_checks flag instead of the dangerous command prevention setting so health checks remain enabled by default

Testing

• python -m pytest -o addopts="" tests/unit/openai_connector_tests/openai_logging_test.py
• python -m pytest -o addopts=""

---

https://chatgpt.com/codex/tasks/task_e_68ec26beb3b0833397f9204b4e11ff80

Summary by CodeRabbit

• Refactor
  • Consolidated the health check toggle into a single configuration setting, replacing the previous nested key.
  • Default behavior remains unchanged; environments using the old key should switch to the new setting for consistent behavior.
  • No changes to public interfaces or commands.

[coderabbitai]

Walkthrough

The initialization logic in src/connectors/openai.py now determines whether to disable health checks by reading an AppConfig attribute (disable_health_checks) via getattr, replacing the previous nested config key lookup ("session.dangerous_command_prevention_enabled").

Changes

Cohort / File(s)	Summary
Config flag source update src/connectors/openai.py	Replace nested config key bool(self.config.get("session.dangerous_command_prevention_enabled", False)) with bool(getattr(self.config, "disable_health_checks", False)) to control health-check behavior during initialization.

Sequence Diagram(s)

sequenceDiagram
    autonumber
    actor User
    participant App as Application
    participant Cfg as AppConfig
    participant Conn as OpenAIConnector

    User->>App: start()
    App->>Cfg: load configuration
    App->>Conn: initialize(conn_config=Cfg)

    note over Conn: Determine health-check behavior
    Conn->>Cfg: getattr(Cfg, "disable_health_checks", False)
    alt disable_health_checks == True
        note right of Conn: Health checks disabled
        Conn-->>App: init complete (no health checks)
    else
        note right of Conn: Health checks enabled
        Conn-->>App: init complete (health checks on)
    end

Loading

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Poem

A twitch of whiskers, a toggle flips,

From nested keys to cleaner tips.

I hop through configs, light and swift,

One attribute—behold the shift!

Health checks on or quietly still,

A tidy warren, code by will.

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run @coderabbitai generate docstrings to improve docstring coverage.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title Check	✅ Passed	The title succinctly and accurately describes the main change—updating the OpenAI connector’s health check configuration—so it clearly communicates the focus of the pull request.

✨ Finishing touches

• 📝 Generate docstrings

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Post copyable unit tests in a comment
• Commit unit tests in branch codex/fix-a-selected-bug-after-analysis-wnkzbx

---

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[coderabbitai]

Actionable comments posted: 1

📜 Review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between dd216cf and 7556db7.

📒 Files selected for processing (1)

• src/connectors/openai.py (1 hunks)

🧰 Additional context used

📓 Path-based instructions (2)

**/*.py

📄 CodeRabbit inference engine (AGENTS.md)

**/*.py: Avoid using emojis in Python code comments or docstrings
Follow PEP 8 and use type hints for all functions
Import order must be: standard library, third-party, then local imports, separated by blank lines
Naming conventions: snake_case for variables and functions; PascalCase for classes
Error handling: use specific exceptions and include meaningful error messages
Prefer f-strings for string formatting

Files:

• src/connectors/openai.py

src/**/*.py

📄 CodeRabbit inference engine (AGENTS.md)

src/**/*.py: Catch specific exceptions; avoid broad except Exception blocks
If a broad exception must be caught, log with exc_info=True and re-raise a specific custom exception
Use the most specific exception class from src.core.common.exceptions that accurately describes the error
Provide clear, helpful error messages and include relevant details in the details dictionary of custom exceptions

Files:

• src/connectors/openai.py

🧬 Code graph analysis (1)

src/connectors/openai.py (2)

tests/unit/core/services/test_json_repair_middleware_gate.py (1)

• config (17-30)

tests/unit/core/services/test_json_repair_middleware.py (1)

• config (18-24)

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (2)

• GitHub Check: test (3.10)
• GitHub Check: Analyze (python)

[coderabbitai]

⚠️ Potential issue | 🔴 Critical

🧩 Analysis chain

Good change to use a dedicated health check flag, but verify the attribute exists on AppConfig.

The shift from session.dangerous_command_prevention_enabled to a top-level disable_health_checks attribute is architecturally sound and aligns with the PR objective of using a dedicated configuration flag for health checks.

However, please verify that:

1. The disable_health_checks attribute is actually defined on the AppConfig class
2. No other code still references session.dangerous_command_prevention_enabled for health check purposes
3. Tests are updated to use the new configuration attribute

Run the following verification scripts:

---

🏁 Script executed:

#!/bin/bash
# Description: Verify that disable_health_checks attribute exists on AppConfig class

# Find the AppConfig class definition and check for disable_health_checks attribute
echo "=== Searching for AppConfig class definition and disable_health_checks attribute ==="
ast-grep --pattern $'class AppConfig$$$:
  $$$
  disable_health_checks$$$
  $$$'

# Alternative: search for the attribute definition in config files
echo -e "\n=== Searching for disable_health_checks in config-related files ==="
rg -n --type=py -C5 'disable_health_checks' -g 'src/core/config/**'

Length of output: 1936

---

🏁 Script executed:

#!/bin/bash
# Description: Check for any remaining references to the old config key

# Search for any code still using session.dangerous_command_prevention_enabled
echo "=== Searching for old config key references ==="
rg -n --type=py 'dangerous_command_prevention_enabled' -C3

# Check if this key is still being set or read elsewhere
echo -e "\n=== Checking for session config with dangerous_command_prevention ==="
rg -n --type=py 'SessionConfig.*dangerous' -C3

Length of output: 3619

---

Update remaining references to session.dangerous_command_prevention_enabled

• Remove dangerous_command_prevention_enabled field and its env-var mapping in src/core/config/app_config.py.
• In src/core/persistence.py::_should_raise_strict_errors, replace config.get("session.dangerous_command_prevention_enabled") with config.disable_health_checks.
• In src/core/di/services.py (around line 1052), use not app_config.disable_health_checks instead of app_config.session.dangerous_command_prevention_enabled.
• In tests/utils/app_builder.py, set AppConfig.disable_health_checks rather than the old session flag.

🤖 Prompt for AI Agents

In src/connectors/openai.py around lines 74-76, replace the getattr(self.config,
"disable_health_checks", False) pattern with direct use of the new boolean
attribute config.disable_health_checks (rename local variable to something like
disable_health_checks) and use that value where needed; additionally, remove any
remaining references to session.dangerous_command_prevention_enabled across the
codebase: delete the field and its env-var mapping in
src/core/config/app_config.py, update
src/core/persistence.py::_should_raise_strict_errors to use
config.disable_health_checks instead of
config.get("session.dangerous_command_prevention_enabled"), change the check in
src/core/di/services.py (around line 1052) to use not
app_config.disable_health_checks in place of
app_config.session.dangerous_command_prevention_enabled, and update
tests/utils/app_builder.py to set AppConfig.disable_health_checks rather than
the old session flag.