Who contributed to anurag629 on July 31, 2026?

1 developer shipped this update, including anurag629.

What were the notable anurag629 updates?

Run OpenAI on /v1/responses and make response_format real and Run OpenAI on /v1/responses and make response_format real (#18).

@anurag629

361 stories across 44 days in 2026, 101-day streak

Mon Wed Fri

Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

Mon Wed Fri

Jan Feb Mar Apr May Jun Jul Aug Sep Oct Nov Dec

an entry to read activity only Less More before entries began Recent weeks →

Entries start Jan 13, 2022 — we reconstructed the previous month from @anurag629's public GitHub activity on the day they joined. Squares before that show contribution counts only.

Full archive →

Friday, July 31, 2026

OpenAI responses transport and response format handling

By RepoJournal , from @anurag629's public GitHub activity

1 person shipped this

anurag629 @anurag629 2 cited

Anurag merged a major refactor of OpenAI integration in luca-py, moving to the /v1/responses endpoint and making response_format a real, opaque data structure that survives model switches.

The core work landed in quantized-ai/luca-py with a new `OpenAIResponsesTransport` that runs alongside the existing `OpenAITransport` [1] [2]. The new transport swaps `messages` for `input` items, `choices` for `output` items, and replaces delta chunks with typed SSE events. It also surfaces `status` and `incomplete_details` instead of `finish_reason`, aligning with OpenAI's current API shape. A five-reviewer pass surfaced three merge blockers, all confirmed against the live OpenAI and Anthropic APIs, which Anurag fixed in the final commit [1]. The work closes issue #4 by making provider-owned opaque data survive a model switch, the shared problem between the responses endpoint move and response_format handling. A single commit also landed to anurag629/anurag629 updating the README.

References

[1] Run OpenAI on /v1/responses and make response_format real ↗ quantized-ai/luca-py
[2] Run OpenAI on /v1/responses and make response_format real (#18) quantized-ai/luca-py

Quick answers

What shipped in anurag629 on July 31, 2026?: Anurag merged a major refactor of OpenAI integration in luca-py, moving to the /v1/responses endpoint and making response_format a real, opaque data structure that survives model switches. In total, 2 commits and 1 pull requests landed.
Who contributed to anurag629 on July 31, 2026?: 1 developer shipped this update, including anurag629.
What were the notable anurag629 updates?: Run OpenAI on /v1/responses and make response_format real and Run OpenAI on /v1/responses and make response_format real (#18).

Model catalog switched to models.dev

Anurag Verma replaced two drifting hand-maintained lists with a live feed from models.dev, fixing pricing data that was off by 3x for some models.

2 shipped

@anurag629 Aug 3

Session storage overhaul and per-model system prompts

Anurag Verma landed two major features in quantized-ai/luca-py, moving session files out of project directories and adding model-aware prompts to the agent.

4 shipped

@anurag629 Aug 2