open-code-review/internal
kite f054bb799e fix: propagate LLM API errors instead of showing misleading "Looks good to me"
When all subtask LLM calls fail (e.g. invalid API key), dispatchSubtasks
now returns an error instead of empty comments with nil error. Partial
failures are recorded as subtask_error warnings so output functions can
distinguish "no issues found" from "review failed".
2026-05-22 15:28:26 +08:00
..
agent fix: propagate LLM API errors instead of showing misleading "Looks good to me" 2026-05-22 15:28:26 +08:00
config feat: init 2026-05-20 22:03:52 +08:00
diff feat: init 2026-05-20 22:03:52 +08:00
llm feat: init 2026-05-20 22:03:52 +08:00
model feat: init 2026-05-20 22:03:52 +08:00
session feat: init 2026-05-20 22:03:52 +08:00
stdout feat: init 2026-05-20 22:03:52 +08:00
suggestdiff feat: init 2026-05-20 22:03:52 +08:00
telemetry feat: init 2026-05-20 22:03:52 +08:00
tool feat: init 2026-05-20 22:03:52 +08:00
viewer feat: init 2026-05-20 22:03:52 +08:00