Haozhe a74ab44ac7 feat: raise default per-step LLM retry budget to 10 attempts (#1740) ... * feat: raise default per-step LLM retry budget to 10 attempts The default of 3 attempts only produced ~1.5s of backoff (0.5s/1s), so sustained provider overload (429) surfaced to the user almost immediately. With 10 attempts the exponential ramp (500ms base, x2, 32s cap, 25% jitter) waits out multi-minute overload windows before failing the turn. Applies to both agent-core (chatWithRetry) and agent-core-v2 (stepRetry service); loop_control.max_retries_per_step still overrides. * test(agent-core): pin retry-dependent tests to the new default budget - error-paths: the warn-log attempt field now reads 1/10 with the default 10-attempt budget - goal-session pause tests: every LLM call throws a retryable error, so the default 10-attempt backoff (~2min) blew the 5s test timeout; pin maxRetriesPerStep=1 since the pause behavior does not depend on the retry count		2026-07-15 15:24:17 +08:00
..
config-files.md	feat: raise default per-step LLM retry budget to 10 attempts (#1740)	2026-07-15 15:24:17 +08:00
data-locations.md	feat(update): roll out automatic updates in staged batches via CDN manifest (#691)	2026-06-15 16:52:44 +08:00
env-vars.md	docs: update subagent timeout docs for configurable timeout_ms (#1582)	2026-07-12 21:09:17 +08:00
overrides.md	feat(cli): add -c as shorthand for --continue (#999)	2026-06-23 13:53:31 +08:00
providers.md	fix(provider): honor base_url for google-genai and vertexai providers (#1269)	2026-07-01 19:33:35 +08:00