shern-point f702d45a24 feat: route OpenAI chat usage through preserved prompt text ...

Use the stored full-context prompt text for chat non-stream, stream, and retry accounting so current_input_file no longer shrinks returned prompt token counts.

2026-04-30 00:45:30 +08:00

..

chat_history_test.go

refactor: thread tool schemas through chat tool outputs

2026-04-28 13:38:57 +08:00

chat_history.go

refactor backend API structure

2026-04-26 06:58:20 +08:00

chat_stream_runtime.go

feat: route OpenAI chat usage through preserved prompt text

2026-04-30 00:45:30 +08:00

empty_retry_runtime.go

feat: route OpenAI chat usage through preserved prompt text

2026-04-30 00:45:30 +08:00

handler_chat_auto_delete_test.go

refactor backend API structure

2026-04-26 06:58:20 +08:00

handler_chat.go

feat: route OpenAI chat usage through preserved prompt text

2026-04-30 00:45:30 +08:00

handler_toolcall_test.go

test: cover chat string-protected tool arguments

2026-04-28 13:45:35 +08:00

handler.go

refactor: thread tool schemas through chat tool outputs

2026-04-28 13:38:57 +08:00

test_helpers_test.go

增加不同上下文模式

2026-04-26 14:21:15 +08:00

vercel_prepare_test.go

Revert "refactor: consolidate current_input_file prompt into BuildOpenAICurrentInputContextPrompt"

2026-04-28 00:31:12 +08:00

vercel_stream.go

refactor: replace history_split with current_input_file configuration

2026-04-27 23:36:56 +08:00