Devika Verma a217511d50 Responses stream: rebuild the turn when the terminal event's output is empty ...

Some backends only stream output items and never repeat them on completed;
collect output_item.done as the fallback so text and tool calls survive.

2026-08-21 16:27:25 -07:00

..

__init__.py

Provider: ChatGPT-subscription sign-in (OAuth PKCE, tokens local-only)

2026-08-21 15:18:45 -07:00

anthropic_provider.py

Diagnose truncated tool calls instead of executing their mangled args

2026-08-15 06:55:10 -07:00

base.py

Merge branch 'main' of https://github.com/andrewyng/openworker into issue/ope-46

2026-07-29 12:07:07 +05:30

bedrock_provider.py

Meter token usage across all model providers

2026-07-27 21:01:31 -07:00

capabilities.py

Add Google Vertex AI provider with per-family dispatch

2026-07-25 16:19:00 -07:00

codex_auth.py

Provider: ChatGPT-subscription sign-in (OAuth PKCE, tokens local-only)

2026-08-21 15:18:45 -07:00

codex_provider.py

Provider: ChatGPT-subscription sign-in (OAuth PKCE, tokens local-only)

2026-08-21 15:18:45 -07:00

errors.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

gemini_provider.py

Meter token usage across all model providers

2026-07-27 21:01:31 -07:00

matrix.py

Subscription catalog: add the 5.6 tiers (Sol/Terra/Luna); Sol becomes the recommended model

2026-08-21 16:10:51 -07:00

openai_provider.py

OpenAI-compatible path names an output ceiling instead of trusting server defaults

2026-08-15 13:47:34 -07:00

openai_responses.py

Responses stream: rebuild the turn when the terminal event's output is empty

2026-08-21 16:27:25 -07:00

registry.py

Subscription catalog: add the 5.6 tiers (Sol/Terra/Luna); Sol becomes the recommended model

2026-08-21 16:10:51 -07:00

router.py

OpenWorker: initial import

2026-07-21 11:09:41 -07:00

vertex_provider.py

Vertex: countTokens verify, global-location host, honest region help

2026-07-27 12:58:16 -07:00