6 Commits

Author	SHA1	Message	Date
hub-gif	9797796f2e	fix(pipeline): cap LLM brief size on report regen; enrich chat HTTP errors ... Regenerate-report (llm) used compact_brief_for_llm default 350k chars, unlike other LLM steps (80k–100k), which can cause gateway timeouts or 5xx surfacing as 502. chat_completion_text now attaches response body snippet to HTTPError for easier diagnosis. Made-with: Cursor	2026-04-14 09:55:42 +08:00
hub-gif	a8210ec933	feat(报告): 各章大模型衔接分析与 report_config 开关 ... Made-with: Cursor	2026-04-13 11:06:35 +08:00
hub-gif	ed2738953f	refactor(报告): 全文大模型补充改为嵌入第八章末而非篇首 ... Made-with: Cursor	2026-04-13 10:54:43 +08:00
hub-gif	bac71c00be	feat(报告): 评价大模型解读强化负向主题归因与抽样 ... Made-with: Cursor	2026-04-13 10:52:14 +08:00
hub-gif	7fc59e5c5f	fix(pipeline): 报告重生成时路径与数据错误统一返回 400 ... Made-with: Cursor	2026-04-13 10:36:25 +08:00
hub-gif	d8086dfdd5	Initial commit: Market-Assistant standalone (Django + Vue + JD crawler copy) ... Made-with: Cursor	2026-04-10 18:03:35 +08:00