claude-code

mirror of https://github.com/instructkr/claude-code.git synced 2026-06-06 04:06:45 +00:00

Files

Petter Reinholdtsen 1d516be779 fix: recover from llama.cpp context overflow and reqwest SSE decode failures

Extend auto-compaction error detection to handle additional error patterns
from llama.cpp backends: 'Context size has been exceeded',
'exceed_context_size_error', 'exceeds the available context size'. Also
recover from reqwest 'error decoding response body' errors — some
llama.cpp instances return a non-SSE plaintext HTTP 500 on context overflow,
causing the SSE deserializer to fail.

Add dynamic threshold adaptation: parse server-reported context window
size from error messages (e.g., '(81920 tokens)') and set the auto-
compaction trigger at 70% of that value. This replaces the need for a
hardcoded threshold, adapting automatically to any backend's limits.

This patch was developed with assistance from OpenCode and local Qwen 3.6
API server.

2026-05-27 16:57:59 +02:00

api

fix(#754 ): missing_credentials hint now newline-delimited so JSON hint field is non-null

2026-05-26 21:23:03 +09:00

claw-analog

Reject drifted claw-analog bootstrap phases

2026-05-25 19:33:37 +00:00

claw-rag-service

feat(rag): add claw-rag-service

2026-05-25 11:25:25 +09:00

commands

fix(#805 ): skills show <not-found> in text mode silently returned empty success instead of error