lilong.129 90ce090e35 fix: remove redundant message cleaning logic in callModelWithLogging ...

The previous message cleaning logic was flawed:
- cleanedMsg.Content was already set to message.Content
- The condition checked if message.Content == "" then set cleanedMsg.Content = ""
- This was redundant since cleanedMsg.Content would already be empty

The real fix for the API 400 error is in planner.go where we ensure Tool messages
have non-empty content. The utils.go changes were unnecessary.

2025-06-26 13:41:39 +08:00

..

testdata

refactor: ai asserter

2025-04-29 20:08:22 +08:00

ai_test.go

feat: optimize ILLMService interface to support different models for each component

2025-06-11 12:18:31 +08:00

ai.go

feat: optimize ILLMService interface to support different models for each component

2025-06-11 12:18:31 +08:00

asserter_prompts.go

refactor: json asserter

2025-05-22 18:22:12 +08:00

asserter_test.go

feat: enhance AI result handling with model name and usage statistics for query, action, and assertion types

2025-06-24 15:25:12 +08:00

asserter.go

feat: enhance AI result handling with model name and usage statistics for query, action, and assertion types

2025-06-24 15:25:12 +08:00

converter_test.go

feat: add MCP tools registration to LLM service

2025-06-09 22:19:43 +08:00

converter.go

feat: add MCP tools registration to LLM service

2025-06-09 22:19:43 +08:00

cv_vedem_test.go

refactor: NewXTDriver api, return error if init failed

2025-04-30 14:31:36 +08:00

cv_vedem.go

fix: add missing action options

2025-06-19 21:57:26 +08:00

cv.go

refactor: NewXTDriver api, return error if init failed

2025-04-30 14:31:36 +08:00

env_test.go

feat: implement multi-model service configuration support

2025-06-06 22:17:59 +08:00

env.go

change: set llm timeout to 120s

2025-06-09 22:42:19 +08:00

parser_default.go

feat: implement structured response parsing with enhanced error recovery and UTF-8 sanitization

2025-06-18 16:59:35 +08:00

parser_test.go

fix: add direction parameter support for scroll operations in UI-TARS parser

2025-06-10 16:40:10 +08:00

parser_ui_tars.go

fix: add direction parameter support for scroll operations in UI-TARS parser

2025-06-10 16:40:10 +08:00

planner_prompts.go

feat: add home and back action mappings to planner prompts

2025-06-18 12:01:53 +08:00

planner_test.go

docs: update AI module README with latest features

2025-06-10 20:52:44 +08:00

planner.go

fix: remove redundant message cleaning logic in callModelWithLogging

2025-06-26 13:41:39 +08:00

querier_prompts.go

feat: add AI Querier module with custom output schema support and refactor common model calling logic

2025-06-10 20:41:35 +08:00

querier_test.go

feat: enhance AI result handling with model name and usage statistics for query, action, and assertion types

2025-06-24 15:25:12 +08:00

querier.go

feat: enhance AI result handling with model name and usage statistics for query, action, and assertion types

2025-06-24 15:25:12 +08:00

session.go

refactor: replace hardcoded log messages with constants for better maintainability

2025-06-18 17:17:29 +08:00

utils_test.go

feat: implement structured response parsing with enhanced error recovery and UTF-8 sanitization

2025-06-18 16:59:35 +08:00

utils.go

fix: remove redundant message cleaning logic in callModelWithLogging

2025-06-26 13:41:39 +08:00