2 Commits

Include renames

Author	SHA1	Message	Date
Eric Wang	a5407e03b2	feat(agent): align prompts and runtime with workflow@20261020 ... - archive workflow/20261020 export (diff vs 20261016: collection prompt only - state-decides-body rule, route when info complete) - prompts: collection.md updated; 6 photo/confirm prompts archived with source nodeIds; render_prompt replaces {{$vars}} (Asia/Shanghai clock, person fields, explicit 'not provided' for missing prefills) - llm: message history passed as user/assistant roles (chatNode history=50); optional LLM_TEMPERATURE; FakeLLMService supports history-aware responders - collect: context via system supplement, raw user input as user message (Text Editor#2 parity), shared validated_reply (one call, one repair) - welcome: Assigned Reply#3 original text, stored in dialogue history - transitions: 2004 plate-confirm entries (2003->2004/2005, 2004->2005) - verified: prompt files byte-identical to workflow JSON (parametrized test)	2026-10-21 15:10:51 +08:00
Eric Wang	1c6b1a513d	feat(agent): LLM-powered collection node with welcome stage and session-scoped delete (assignment 4) ... - prompts/collection.md: versioned collection system prompt extracted from workflow node yQaBxfrWjbRr with source/version/porting notes - llm.py: LLMService protocol; FakeLLMService (scripted, records calls); OpenAILLMService (async, wait_for timeout with cancellation, retry only on timeout/429/connection, errors normalized) - collect.py: run_collect reference impl - one LLM call produces state prefix + body, controlled repair (max 1 retry) for missing prefix or illegal stage proposal, whitelist guard, CollectReplyError without raw model content; dialogue history + confirmed fields injected into prompt so the model skips known info (作业4-5) - fields.py / clock.py: three-state field candidates (unknown/ candidate/confirmed), per-type validation (count not inferred from description, future time rejected), injectable Clock - graph.py: welcome node - first message returns fixed 1001 greeting without LLM (mirrors workflow is_first_message -> Assigned Reply#3), route empty stage to welcome - endpoints/delete_session: backend switch - langgraph clears graph checkpoint, fastgpt path unchanged - config: AGENT_LLM_PROVIDER fake|openai with validation - untrack .env (secrets), move template to root .env.example Verified: - pytest 103 passed; smoke turns 1/2/1 - Real LLM e2e: POST /chat multi-turn context works - Golden eval collection_skip_known_info: 12/12 cases pass - Golden eval no_false: 8/10 cases pass; 4 confirm/photo cases fail at final step - model routes on short reply '对' (prompt-adherence gap, photo/confirm stages are assignment 5 scope); recorded in evals/results/20261020-144856 Known limits: field extraction from model reply not wired (stub); photo/confirm nodes still scaffold; clarify counting is approximate.	2026-10-20 14:53:46 +08:00