WeKnora/internal/agent
wizardchen 1f5970b67e refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer
The Agent ran a parallel context cache (Redis/in-memory) on top of the
messages table to feed multi-turn history into the LLM. That dual-write
caused subtle drift (e.g. compression diverging from DB, system-prompt
swaps lost on restart) and required a separate ClearContext path on
session/IM clear.

Make the messages table the single source of truth:

- Add service.LoadAgentHistory: rebuilds chat.Message history per turn
  from the persisted messages, expanding AgentSteps into proper OpenAI
  assistant_with_tool_calls + tool messages and replaying the canonical
  final answer (with <think> blocks stripped). final_answer tool calls
  are filtered to avoid duplicating the trailing answer.
- Make AgentEngine stateless across turns: drop ContextManager / sessionID
  cache plumbing from the engine, agent service, and CreateAgentEngine
  signature. The engine only uses sessionID for logging/event emission.
- Wire AgentQA to load history from DB on demand using HistoryTurns
  (default 5) when MultiTurnEnabled, otherwise run with empty history.
- Delete the llmcontext package (ContextManager interface, Redis/memory
  storage, factory) and the SessionService.ClearContext API path; IM
  /clear and session message clear no longer need to invalidate cache.

Behavior preserved: KnowledgeQA-mode replay is unchanged (turns with
empty AgentSteps just produce the single canonical assistant message),
and Agent-mode turns now consistently see prior tool calls and results.
2026-05-12 12:26:24 +08:00
..
approval fix(agent): enhance user authorization and concurrency handling in tool approval 2026-05-10 22:57:12 +08:00
memory feat(agent): enhance message consolidation and context management 2026-03-25 22:08:29 +08:00
skills feat: adapt preloaded skills to smart-reasoning agent 2026-02-04 20:08:49 +08:00
token feat(agent): enhance message consolidation and context management 2026-03-25 22:08:29 +08:00
tools fix(agent): 加固 MCP 工具人审批的跨实例与并发语义 2026-05-10 22:57:12 +08:00
act.go fix(agent): 加固 MCP 工具人审批的跨实例与并发语义 2026-05-10 22:57:12 +08:00
const.go feat: Implement wiki_config updates in knowledge base management 2026-04-22 21:17:21 +08:00
engine.go refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer 2026-05-12 12:26:24 +08:00
engine_image_test.go feat: auto-describe MCP tool result images via VLM 2026-03-25 21:38:15 +08:00
engine_test.go refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer 2026-05-12 12:26:24 +08:00
finalize.go fix(agent): 修复WeKnora对话完前端未显示结束标记问题 2026-05-07 16:34:20 +08:00
langfuse_test.go feat(observability): instrument agent ReAct loop and tool calls in Langfuse 2026-04-24 19:58:08 +08:00
observe.go refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer 2026-05-12 12:26:24 +08:00
observe_test.go fix(agent): terminate ReAct loop on final_answer regardless of arg parse success 2026-04-23 19:36:28 +08:00
prompts.go feat: Update agent type presets and prompt templates for improved knowledge base handling 2026-04-22 21:18:34 +08:00
prompts_wiki.go fix(ingest): stop hallucinating summaries from filenames on empty PDFs 2026-05-06 11:23:32 +08:00
prompts_wiki_test.go feat: Enhance wiki extraction and configuration options 2026-04-22 21:18:32 +08:00
think.go chore(agent): log natural-stop candidate when no tool calls 2026-05-07 18:28:28 +08:00