- --ticker, --date and --analysts answer their steps, checked as the prompts check them; --save/--no-save and --show/--no-show answer the questions after the run
- with no terminal, the run stops before it starts and names every flag or TRADINGAGENTS_* variable still needed; a missing API key and an announcement no longer wait for input
- README shows an unattended run
- every analyst calls its tools through the router, offline; the decision is parsed and logged
- free-text and structured-output paths, and resume from a checkpoint
- remove the unused mock_llm_client fixture
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.
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.
- 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
Yijia-Xiao