TheArchitectit e9e5104a73 fix: model_token_limit catch-all returns None for unknown models ... Restores the fix from @Offwhite-Del that was lost during rebase. Unknown models now return None so preflight skips the context-window check and lets the API enforce its own limits.		2026-07-25 00:47:42 -05:00
..
providers	fix: model_token_limit catch-all returns None for unknown models	2026-07-25 00:47:42 -05:00
client.rs	feat(setup): separate env namespace for custom OpenAI-compat provider	2026-06-30 09:43:39 -05:00
error.rs	feat(team): team enhancements, subagentModel, parallel tool exec	2026-07-24 16:29:58 -05:00
http_client.rs	feat: API timeout config, Retry-After header support, and configurable retry	2026-06-02 15:30:22 -05:00
lib.rs	feat(team): team enhancements, subagentModel, parallel tool exec	2026-07-24 16:29:58 -05:00
prompt_cache.rs	feat(api): add tuning params (temperature, top_p, penalties, stop) to MessageRequest	2026-04-08 07:07:33 +09:00
sse.rs	fix(api): enrich JSON parse errors with response body, provider, and model	2026-04-07 14:22:05 +09:00
types.rs	omx(team): auto-checkpoint worker-1 [1]	2026-05-15 10:21:18 +09:00