jnjpng 778f28ccf3 fix: handle transient network errors in ChatGPT OAuth client (#9462) ...

- Map httpx.ReadError/WriteError/ConnectError to LLMConnectionError in
  handle_llm_error so Temporal correctly classifies them as retryable
  (previously fell through to generic non-retryable LLMError)
- Add client-level retry with exponential backoff (up to 3 attempts) on
  request_async and stream_async for transient transport errors
- Stream retry is guarded by has_yielded flag to avoid corrupting
  partial responses already consumed by the caller

2026-02-24 10:52:07 -08:00

..

sample_response_jsons

merge this (#4759)

2025-09-17 15:47:40 -07:00

__init__.py

merge this (#4759)

2025-09-17 15:47:40 -07:00

anthropic_client.py

fix(core): improve error handling for upstream LLM provider errors (#9423)

2026-02-24 10:52:07 -08:00

anthropic_constants.py

feat: Add structured outputs for Anthropic (#7495)

2026-01-12 10:57:19 -08:00

azure_client.py

fix(core): differentiate BYOK vs base provider in all LLM error details (#9425)

2026-02-24 10:52:07 -08:00

bedrock_client.py

feat: enable bedrock for anthropic models (#8847)

2026-01-19 15:54:44 -08:00

chatgpt_oauth_client.py

fix: handle transient network errors in ChatGPT OAuth client (#9462)

2026-02-24 10:52:07 -08:00

deepseek_client.py

fix(core): sanitize Unicode surrogates in all LLM client requests (#9323)

2026-02-24 10:52:06 -08:00

error_utils.py

fix: handle new openai overflow error format (#7110)

2025-12-17 17:31:02 -08:00

google_ai_client.py

fix(core): use BYOK API keys for Google AI/Vertex LLM requests (#9439)

2026-02-24 10:52:07 -08:00

google_constants.py

fix: max output tokens for gemini 3 models (#7322)

2025-12-17 17:31:03 -08:00

google_vertex_client.py

fix: catch contextwindowexceeded error on gemini (#9450)

2026-02-24 10:52:07 -08:00

groq_client.py

fix(core): sanitize Unicode surrogates in all LLM client requests (#9323)

2026-02-24 10:52:06 -08:00

helpers.py

fix: remove unused sync code (#8613)

2026-01-19 15:54:37 -08:00

llm_api_tools.py

fix: add LLMCallType enum and ensure call_type is set on all provider traces (#9258)

2026-02-24 10:52:06 -08:00

llm_client_base.py

fix(core): differentiate BYOK vs base provider in all LLM error details (#9425)

2026-02-24 10:52:07 -08:00

llm_client.py

feat: openrouter byok (#9148)

2026-01-29 12:44:04 -08:00

minimax_client.py

fix(core): sanitize Unicode surrogates in all LLM client requests (#9323)

2026-02-24 10:52:06 -08:00

mistral.py

fix(core): reject empty API keys in Bearer auth headers (#9350)

2026-02-24 10:52:07 -08:00

openai_client.py

fix: catch contextwindowexceeded error on gemini (#9450)

2026-02-24 10:52:07 -08:00

openai.py

fix(core): reject empty API keys in Bearer auth headers (#9350)

2026-02-24 10:52:07 -08:00

sglang_native_client.py

feat: add log probabilities from OpenAI-compatible servers and SGLang native endpoint (#9240)

2026-02-24 10:52:07 -08:00

together_client.py

fix(core): sanitize Unicode surrogates in all LLM client requests (#9323)

2026-02-24 10:52:06 -08:00

xai_client.py

fix(core): sanitize Unicode surrogates in all LLM client requests (#9323)

2026-02-24 10:52:06 -08:00

zai_client.py

feat: add glm 5 to core (#9436)

2026-02-24 10:52:07 -08:00