Ryan Ward 345057a147 Fix: Ensure OpenAI requests end with user message for Bedrock/LiteLLM compatibility ...

When LiteLLM routes OpenAI-format requests to AWS Bedrock, the provider
rejects conversations ending with an assistant message with:
'This model does not support assistant message prefill.'

Add ensure_ends_with_user_message() as the final sanitization step in
sanitize_messages_for_openai(). If the conversation ends with an assistant
message, a minimal 'Continue.' user message is appended.

Updated tests to reflect the new behavior and added dedicated tests for
the new function.

2026-07-16 09:55:38 -05:00

..

assets

first pass of merging in warp (doesn't build)

2026-07-01 16:08:58 -05:00

channels

first pass of merging in warp (doesn't build)

2026-07-01 16:08:58 -05:00

DockTilePlugin

first pass of merging in warp (doesn't build)

2026-07-01 16:08:58 -05:00

examples

Wrapping up bedrock implementation

2026-05-13 10:04:59 -05:00

resources/tab_configs

Initial commit

2026-04-29 10:43:20 -05:00

src

Fix: Ensure OpenAI requests end with user message for Bedrock/LiteLLM compatibility

2026-07-16 09:55:38 -05:00

tests/ssh

Initial public release of Warp.

2026-04-28 08:43:33 -05:00

build.rs

first pass of merging in warp (doesn't build)

2026-07-01 16:08:58 -05:00

Cargo.toml

Bump version to 2.0.0 and upload install-galaxy.sh in deploy script

2026-07-15 16:17:13 -05:00