Rohit C Prasad 44e0e8566f OpenAI-compatible path names an output ceiling instead of trusting server defaults ...

max_tokens defaults to 32k (compat servers were capping at ~2k, truncating file
writes); a below-limit model 400 drops the param and retries on the server default.

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

..

__init__.py

Route native OpenAI (blank endpoint) to the Responses provider

2026-07-28 20:48:43 +05:30

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

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

models: Kimi K3 via Together (1M window, vision); right-align the more/less toggle

2026-07-30 10:32:47 -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

OpenAI Responses provider: reasoning + tools for native OpenAI models

2026-07-28 20:45:31 +05:30

registry.py

Route native OpenAI (blank endpoint) to the Responses provider

2026-07-28 20:48:43 +05:30

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