4 Commits

Author	SHA1	Message	Date
Yijia-Xiao	65608831f8	fix(data): respect the configured vendor chain and log vendor failures ... The router silently extended every request to all available vendors regardless of config, so an explicit single-vendor choice still fell back to others and returned data from an unexpected source (#988, #289), and serious primary-vendor errors were swallowed without a trace (#989). The configured vendor list is now the exact chain (list several for ordered fallback; "default" uses all), unknown vendors raise, and swallowed vendor errors are logged. Adds an autouse config isolation fixture so vendor config can't leak between tests.	2026-06-13 21:11:25 +00:00
Yijia-Xiao	d0dd0420ad	feat(llm): GLM dual-region split + catalog refresh ... Zhipu serves GLM under two brands with separate accounts (Z.AI international vs BigModel China); the CLI URL pointed at one while the openai_client default pointed at the other. Split into glm + glm-cn with secondary region prompt (same UX as Qwen + MiniMax). Catalog adds glm-5-turbo and glm-4.5-air per docs.z.ai.	2026-05-11 04:19:50 +00:00
Yijia-Xiao	9482cae188	fix: bundle config/recursion/missing-key fixes ... - dataflows/config: deepcopy + one-level dict merge so a partial set_config doesn't clobber sibling defaults - graph: thread max_recur_limit from config to Propagator - openai_client: name the missing env var in the API-key error #788 #764 #680	2026-05-11 02:30:24 +00:00
Yijia-Xiao	f85f5d9f5d	test: lazy-load LLM provider clients and add API-key fixtures so the test suite runs cleanly without credentials (#588)	2026-04-25 07:41:36 +00:00