fix: openai use responses column migration added and minor fixes

[Pratham-Mishra04]

Summary

Add support for OpenAI's Responses API and improve model handling in text completions.

Changes

• Added open_ai_use_responses_api column to the keys table via a new database migration
• Set Object field to "response" when converting to responses-only format
• Updated text completion request to properly parse model strings with provider information
• Enhanced logging plugin to handle responses from the Responses API
• Set default APP_DIR to "temp-something-new" in Makefile

Type of change

• Bug fix
• Feature
• Refactor
• Documentation
• Chore/CI

Affected areas

• Core (Go)
• Transports (HTTP)
• Providers/Integrations
• Plugins
• UI (Next.js)
• Docs

How to test

Test the OpenAI Responses API integration:

# Run with the new APP_DIR setting
make run

# Test text completion with model parsing
curl -X POST http://localhost:8080/v1/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-3.5-turbo", "prompt": "Hello, world!"}'

# Verify responses API format
curl -X POST http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-4", "messages": [{"role": "user", "content": "Hello"}]}'

Breaking changes

• Yes
• No

Related issues

Implements support for OpenAI's Responses API format

Security considerations

No significant security implications.

Checklist

• I read docs/contributing/README.md and followed the guidelines
• I added/updated tests where appropriate
• I updated documentation where needed
• I verified builds succeed (Go and UI)
• I verified the CI pipeline passes locally if applicable

[coderabbitai]

Caution

Review failed

The pull request is closed.

📝 Walkthrough

Summary by CodeRabbit

• New Features

  • Added new chat request options: reasoning effort, response format, and safety identifier.
  • Enhanced telemetry with richer request/response attributes, detailed token usage, and improved cost tracking.
  • Logging now captures final output message and tool calls from generic response payloads.
  • New configuration flag to enable OpenAI Responses API per key.

• Bug Fixes

  • More reliable streaming cleanup and synchronization across chat, audio, and transcription.
  • Finish reason is now propagated on final chat chunks.
  • Consistent handling of stop sequences across providers.

• Refactor

  • Improved model parsing and request mapping.
  • Simplified span emission logic.

• Chores

  • Dependency updates and module housekeeping.
  • Plugin reload/remove keeps in-memory and tracked states in sync.
  • Minor UI accessibility improvement (tab buttons).

✨ 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 10-06-fix_openai_use_responses_column_migration_added_and_minor_fixes

---

📜 Recent review details

Configuration used: CodeRabbit UI

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 6110981 and dac84bd.

⛔ Files ignored due to path filters (2)

• plugins/logging/go.sum is excluded by !**/*.sum
• plugins/otel/go.sum is excluded by !**/*.sum

📒 Files selected for processing (27)

• core/schemas/chatcompletions.go (6 hunks)
• core/schemas/mux.go (1 hunks)
• core/schemas/providers/anthropic/chat.go (1 hunks)
• core/schemas/providers/anthropic/responses.go (2 hunks)
• core/schemas/providers/bedrock/responses.go (1 hunks)
• core/schemas/providers/cohere/responses.go (1 hunks)
• core/schemas/providers/openai/text.go (1 hunks)
• core/schemas/utils.go (0 hunks)
• framework/configstore/migrations.go (2 hunks)
• framework/streaming/accumulator.go (1 hunks)
• framework/streaming/audio.go (2 hunks)
• framework/streaming/chat.go (2 hunks)
• framework/streaming/transcription.go (1 hunks)
• plugins/logging/go.mod (3 hunks)
• plugins/logging/main.go (1 hunks)
• plugins/otel/converter.go (2 hunks)
• plugins/otel/go.mod (1 hunks)
• plugins/otel/grpc.go (1 hunks)
• plugins/otel/main.go (2 hunks)
• tests/core-providers/scenarios/multiple_images.go (1 hunks)
• tests/core-providers/scenarios/reasoning.go (2 hunks)
• tests/core-providers/scenarios/response_validation.go (3 hunks)
• tests/core-providers/scenarios/utils.go (7 hunks)
• transports/bifrost-http/handlers/server.go (2 hunks)
• transports/bifrost-http/integrations/anthropic/types.go (0 hunks)
• transports/bifrost-http/integrations/openai/types.go (0 hunks)
• ui/app/teams-customers/page.tsx (2 hunks)

---

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

[Pratham-Mishra04]

Warning

This pull request is not mergeable via GitHub because a downstack PR is open. Once all requirements are satisfied, merge this PR as a stack on Graphite.
Learn more

• fix: openai use responses column migration added and minor fixes #554 👈 (View in Graphite)
• otel plugin, dynamic plugin reloads, new UI changes and a few bug fixes #470 : 4 other dependent PRs (#485 , #535 , #546 and 1 other)
• v1.3.0 #507 : 4 other dependent PRs (#536 , #556 , #557 and 1 other)
• main

This stack of pull requests is managed by Graphite. Learn more about stacking.