WeKnora/internal/types
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
..
interfaces refactor(agent): rebuild multi-turn history from DB, drop llmcontext layer 2026-05-12 12:26:24 +08:00
agent.go feat: Introduce agent type presets for smart-reasoning mode 2026-04-22 21:18:20 +08:00
agent_test.go Fix system prompt not being used when flag is false 2026-04-15 20:21:12 +08:00
agent_type_preset.go feat: Introduce agent type presets for smart-reasoning mode 2026-04-22 21:18:20 +08:00
builtin_agent_config.go feat: enhance localization and configuration support 2026-03-17 22:23:24 +08:00
chat.go feat(agent): human-in-the-loop approval for MCP tool calls (#1173) 2026-05-10 22:57:12 +08:00
chat_history_config.go feat: implement chat history and retrieval settings 2026-03-09 11:46:56 +08:00
chat_manage.go fix: missing deep copy entity 2026-04-15 20:35:48 +08:00
chunk.go fix(chunker): trim surrounding whitespace before embedding 2026-05-06 21:16:48 +08:00
chunk_contextheader_test.go test(types): regression test that ContextHeader is hidden from JSON 2026-05-06 17:17:07 +08:00
cleanup.go init commit 2025-08-05 15:08:07 +08:00
const.go feat(observability): integrate Langfuse for LLM token tracking and tracing 2026-04-24 10:29:19 +08:00
context_helpers.go fix(i18n): use WEKNORA_LANGUAGE env for prompt language fallback instead of hardcoded zh-CN 2026-04-02 12:01:25 +08:00
context_helpers_test.go refactor: Replace hardcoded language logic with middleware infrastructure 2026-04-22 21:17:17 +08:00
custom_agent.go fix(storage): merge tos/s3/oss/ks3 tenant configs in buildStorageConfig (#1117) 2026-05-06 17:09:42 +08:00
dataset.go init commit 2025-08-05 15:08:07 +08:00
datasource.go feat(observability): extend Langfuse tracing across asynq pipeline 2026-04-24 13:16:47 +08:00
docparser.go fix(chunker): trim surrounding whitespace before embedding 2026-05-06 21:16:48 +08:00
embedding.go perf: 优化FAQ索引更新和删除性能 2026-01-14 17:30:04 +08:00
errors.go init commit 2025-08-05 15:08:07 +08:00
evaluation.go refactor: Update tenant ID handling across the application 2025-11-25 16:30:54 +08:00
event_bus.go refactor: Implement event-driven streaming and enhance session management 2025-11-07 22:41:41 +08:00
extract_graph.go Refactor knowledge post-processing into orchestrator task 2026-04-16 18:13:20 +08:00
faq.go feat(types): enhance FAQ metadata normalization and sanitization 2026-03-19 18:20:09 +08:00
faq_test.go feat(chunk): implement batch deletion for chunks to avoid MySQL placeholder limit 2026-03-19 18:20:09 +08:00
graph.go feat: implement preview of user level memory graph 2026-02-25 14:29:54 +08:00
indexing_strategy.go feat: Add comprehensive documentation for WeKnora knowledge base and wiki features 2026-04-22 21:18:10 +08:00
json.go test(types): add unit test for JSON unmarshalling and validation 2026-04-22 21:17:36 +08:00
json_test.go test(types): add unit test for JSON unmarshalling and validation 2026-04-22 21:17:36 +08:00
knowledge.go feat(datasource): add Yuque (语雀) connector 2026-04-22 16:39:55 +08:00
knowledgebase.go feat(chunker): recursive priority splitting + token-aware budget 2026-05-06 17:17:07 +08:00
knowledgebase_test.go feat: add vector_store_id column to knowledge_bases for per-KB vector store binding 2026-04-20 19:53:44 +08:00
mcp.go feat(agent): human-in-the-loop approval for MCP tool calls (#1173) 2026-05-10 22:57:12 +08:00
memory.go feat: implement preview of user level memory graph 2026-02-25 14:29:54 +08:00
message.go feat(chat_pipeline): enhance query handling with image and attachment metadata 2026-04-14 18:21:12 +08:00
model.go fix(crypto): fail loudly when encrypted DB fields cannot be decrypted 2026-04-30 15:17:56 +08:00
organization.go feat(api): integrate per-organization resource counts into organization listing 2026-02-09 11:40:25 +08:00
placeholder.go feat: enhance localization and configuration support 2026-03-17 22:23:24 +08:00
qa_request.go feat: attachment_support 2026-04-10 12:49:20 +08:00
retrieval_config.go feat(retrieval): configurable RRF parameters per tenant 2026-05-06 17:17:07 +08:00
retriever.go feat: add Tencent VectorDB retriever backend 2026-05-09 13:14:01 +08:00
search.go feat(prompt): enhance context and intent classification in templates 2026-03-26 18:57:12 +08:00
session.go feat(sessions): add keyword search, user-scoped pinning, and IM source visibility 2026-04-30 16:23:00 +08:00
tag.go feat(logger): implement LLM debug logging functionality 2026-04-16 23:15:02 +08:00
task.go feat(observability): extend Langfuse tracing across asynq pipeline 2026-04-24 13:16:47 +08:00
task_dead_letter.go perf(wiki-ingest): scale to 4w-doc KBs + generic task queue / dead-letter 2026-05-10 00:01:06 +08:00
task_pending_op.go perf(wiki-ingest): scale to 4w-doc KBs + generic task queue / dead-letter 2026-05-10 00:01:06 +08:00
tenant.go feat: support Tencent VectorDB keyword retrieval 2026-05-10 00:02:05 +08:00
tenant_test.go feat: support Tencent VectorDB keyword retrieval 2026-05-10 00:02:05 +08:00
tracing.go feat(observability): extend Langfuse tracing across asynq pipeline 2026-04-24 13:16:47 +08:00
user.go add oidc 2026-03-30 11:13:44 +08:00
vectorstore.go feat: add Tencent VectorDB retriever backend 2026-05-09 13:14:01 +08:00
vectorstore_test.go feat: add Tencent VectorDB retriever backend 2026-05-09 13:14:01 +08:00
web_search.go fix(web-search): normalize default tenant web search config at runtime 2026-04-30 15:28:35 +08:00
web_search_provider.go feat(web-search): add SearXNG provider (#1166) 2026-05-11 16:53:47 +08:00
web_search_test.go fix(web-search): normalize default tenant web search config at runtime 2026-04-30 15:28:35 +08:00
weknoracloud.go refactor(weknoracloud): update credential handling and configuration 2026-04-15 11:37:24 +08:00
wiki_log_entry.go perf(wiki): move ingest log to event table and index to on-demand API 2026-05-08 21:48:52 +08:00
wiki_page.go perf(wiki-ingest): scale to 4w-doc KBs + generic task queue / dead-letter 2026-05-10 00:01:06 +08:00
wiki_page_test.go feat: Enhance wiki extraction and configuration options 2026-04-22 21:18:32 +08:00