Clayton Brown 872ec8d119 feat: spend limits with automatic abort (#524) ... Add --max-cost flag (USD) to cap LLM spend per analysis run. Review feedback applied: - Guard trace[-1] IndexError when stream yields no chunks - Remove speculative model entries from pricing table - Move budget checks inside lock for thread safety - Split log_ticker_spend into format + log for modularity Closes #524		2026-04-20 22:41:10 +10:00
..
agents	fix: process all chunk messages for tool call logging, harden memory score normalization (#534, #531)	2026-04-13 07:21:33 +00:00
dataflows	fix: add missing pandas import in y_finance.py (#488)	2026-04-04 07:14:10 +00:00
graph	feat: spend limits with automatic abort (#524)	2026-04-20 22:41:10 +10:00
llm_clients	feat: add DeepSeek, Qwen, GLM, and Azure OpenAI provider support	2026-04-13 07:12:07 +00:00
__init__.py	feat: spend limits with automatic abort (#524)	2026-04-20 22:41:10 +10:00
default_config.py	feat: spend limits with automatic abort (#524)	2026-04-20 22:41:10 +10:00
spend_tracker.py	feat: spend limits with automatic abort (#524)	2026-04-20 22:41:10 +10:00