Mario Zechner 4f004adefa fix(coding-agent): reset retry counter after each successful LLM response ...

Previously, within a single tool-use turn, rate limit retries would
accumulate across separate LLM calls. For example, if each of 3 tool
calls hit a 429 and retried once, the counter would show '3/3' and fail
even though each individual retry succeeded.

Now the counter resets immediately when a successful (non-error)
assistant message arrives, so each LLM call gets a fresh set of retries.

Fixes #1019

2026-01-29 01:12:29 +01:00

..

agent

Add [Unreleased] section for next cycle

2026-01-27 00:15:42 +01:00

ai

fix(ai): 429 rate limit errors no longer trigger auto-compaction

2026-01-29 00:43:38 +01:00

coding-agent

fix(coding-agent): reset retry counter after each successful LLM response

2026-01-29 01:12:29 +01:00

mom

Add [Unreleased] section for next cycle

2026-01-27 00:15:42 +01:00

pods

Release v0.50.1

2026-01-27 00:14:58 +01:00

tui

feat(tui,coding-agent): add shell-style keybindings alt+b, alt+f, ctrl+d

2026-01-29 00:21:39 +01:00

web-ui

feat(web-ui): export CustomProviderCard, ProviderKeyInput, AbortedMessage, ToolMessageDebugView (fixes #1015)

2026-01-28 02:02:14 +00:00