- reasoning_effort was forwarded only to IDs matching gpt-5 or the o-series, so
GPT-6 models silently dropped the configured effort; match GPT-5 and later,
with a version boundary so unrelated IDs do not match
- Gemini Pro, 3.8+ and the -latest aliases reject thinking_level "minimal"
with a 400; send it only to numbered Flash models before 3.8 and map it to
"low" elsewhere, since aliases move between generations
Interactive selections and flag defaults overrode TRADINGAGENTS_* env vars.
Rule: an explicit env value or CLI flag wins; otherwise the env-applied
default is kept.
- Research depth: skip the prompt when both round-count env vars are set, and
stop overwriting them (#977).
- Checkpoint: --checkpoint/--no-checkpoint is tri-state; omitting it keeps
TRADINGAGENTS_CHECKPOINT_ENABLED (#976).
- Docker ollama: use TRADINGAGENTS_LLM_PROVIDER + OLLAMA_BASE_URL, not a bare
LLM_PROVIDER the overlay never reads (#975).
- Reasoning/thinking knobs: settable via env; the prompt is skipped when set.
- Effort gating: forward effort only to models that accept it (Anthropic
Opus 4.5+/Sonnet 4.6+, OpenAI reasoning models); drop it elsewhere.
- Boolean env values: raise a named error on invalid input instead of
silently becoming False.
