open-code-review/internal
kite 8e9772baa8 fix(llm): add context support to StreamCompletion and memory compression to prevent infinite timeouts
StreamCompletion used http.NewRequest without context and retry with
context.Background(), making streaming calls uncancellable. Memory
compression called Completions() without context, leaving async
goroutines unable to be cancelled or timed out.

- Add StreamCompletionWithCtx to LLMClient interface and both
  OpenAI/Anthropic implementations
- Propagate context through runCompression, addNextMessage, and
  triggerAsyncCompression call chain
- Add 5-minute timeout cap on async compression goroutines
- Cancel in-flight compression HTTP requests when job is superseded
2026-06-06 13:22:32 +08:00
..
agent fix(llm): add context support to StreamCompletion and memory compression to prevent infinite timeouts 2026-06-06 13:22:32 +08:00
config fix(tool): use fixed-string matching by default in code_search to fix Linux failures 2026-06-05 23:59:01 +08:00
diff fix(llm): add context support to StreamCompletion and memory compression to prevent infinite timeouts 2026-06-06 13:22:32 +08:00
llm fix(llm): add context support to StreamCompletion and memory compression to prevent infinite timeouts 2026-06-06 13:22:32 +08:00
model feat: init 2026-05-20 22:03:52 +08:00
release fix(build): improve Windows support based on PR #13 review feedback 2026-06-02 22:37:27 +08:00
session feat(session,viewer): record review mode and diff refs in session 2026-06-05 09:44:33 +08:00
stdout style: apply go fmt formatting 2026-06-03 17:34:28 +08:00
suggestdiff feat: init 2026-05-20 22:03:52 +08:00
telemetry style: apply go fmt formatting 2026-06-03 17:34:28 +08:00
tool fix(tool): use fixed-string matching by default in code_search to fix Linux failures 2026-06-05 23:59:01 +08:00
viewer feat(session,viewer): record review mode and diff refs in session 2026-06-05 09:44:33 +08:00