refac
Some checks failed
Python CI / Ruff Format (3.11) (push) Has been cancelled
Python CI / Ruff Format (3.12) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args: free_disk:false name:main suffix:]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true USE_CUDA_VER=cu126 free_disk:true name:cuda126 suffix:-cuda126]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/amd64 runner:ubuntu-latest], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args: free_disk:false name:main suffix:]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true USE_CUDA_VER=cu126 free_disk:true name:cuda126 suffix:-cuda126]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_CUDA=true free_disk:true name:cuda suffix:-cuda]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_OLLAMA=true free_disk:false name:ollama suffix:-ollama]) (push) Has been cancelled
Create and publish Docker images with specific build args / build (map[arch:linux/arm64 runner:ubuntu-24.04-arm], map[build_args:USE_SLIM=true free_disk:false name:slim suffix:-slim]) (push) Has been cancelled
Frontend Build / Format & Build (push) Has been cancelled
Frontend Build / Unit Tests (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-cuda126, cuda126) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-ollama, ollama) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-slim, slim) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:cuda suffix:-cuda]) (push) Has been cancelled
Create and publish Docker images with specific build args / notify-helm-charts (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:cuda126 suffix:-cuda126]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:main suffix:]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:ollama suffix:-ollama]) (push) Has been cancelled
Create and publish Docker images with specific build args / merge (map[name:slim suffix:-slim]) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (, main) (push) Has been cancelled
Create and publish Docker images with specific build args / copy-to-dockerhub (-cuda, cuda) (push) Has been cancelled

This commit is contained in:
Timothy Jaeryang Baek 2026-09-06 23:23:59 -04:00
parent 3795d5b292
commit 57acc2b68f

View file

@ -1569,6 +1569,20 @@ async def generate_chat_completion(
is_responses = api_config.get('api_type') == 'responses'
# Explicit continuation keeps llama.cpp from echoing the prefill in streamed replies.
if (
api_config.get('provider') == 'llama.cpp'
# These flags apply to Chat Completions, not the Responses API.
and not is_responses
# The frontend sends this ID when the user clicks Continue.
and (metadata or {}).get('assistant_message_id')
# Tool follow-ups retain the metadata but must start a new assistant turn.
and payload.get('messages')
and payload['messages'][-1].get('role') == 'assistant'
):
payload['continue_final_message'] = True
payload['add_generation_prompt'] = False
if api_config.get('azure') or api_config.get('provider') == 'azure':
# Only set api-key header if not using Azure Entra ID authentication
auth_type = api_config.get('auth_type', 'bearer')