fix(cli): don't brick the chat REPL when the first turn fails upstream #110

Merged
michal merged 1 commits from fix/chat-repl-thread-brick into main 2026-08-10 21:55:11 +00:00

1 Commits

Author SHA1 Message Date
Michal
ac5dee906e fix(cli): don't brick the chat REPL when the first turn fails upstream
Some checks failed
CI/CD / typecheck (pull_request) Successful in 1m20s
CI/CD / lint (pull_request) Successful in 2m48s
CI/CD / test (pull_request) Successful in 1m24s
CI/CD / build (pull_request) Successful in 2m40s
CI/CD / smoke (pull_request) Failing after 3m46s
CI/CD / publish (pull_request) Has been skipped
Observed live: turn 1 died with an anthropic 429 before the stream's `final`
frame, streamOnce resolved '' as the thread id, the REPL stored it, and every
later message sent `threadId: ""` — rejected by mcpd's z.string().min(1) with
HTTP 400. Permanently stuck: no turn could succeed again, so no `final` frame
could ever repair the id.

Two independent layers:
- streamOnce now resolves `string | undefined` — undefined when no `final`
  frame arrived — and the REPL keeps its previous thread state on undefined
  instead of overwriting it. One-shot mode skips the `(thread: ...)` footer
  when there is none to report.
- chatBody refuses to serialize an empty threadId at all, so even a leaked ''
  can never reach the wire.

Regression cover in chat-thread-brick.test.ts (7 tests), including the full
REPL chain: failed turn 1 → turn 2 body carries no threadId key. The
assertions are the direct inverse of the old behavior, so they fail pre-fix
by construction.

CLI suite 726 passed, lint clean, tsc clean.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_016dNpnBqyyz9GxfznVcX2sP
2026-08-10 22:54:53 +01:00