mirror of
https://github.com/instructkr/claw-code.git
synced 2026-10-18 00:00:11 +08:00
reacechalmers
fa0d53a969
Two related gaps let a single agentic turn exceed a small context window, with no recovery path once it happened. 1. read_file's character ceiling was a hardcoded 64 KB (~16k tokens), sized for a 200k window. Two reads in one turn reach ~48k tokens, which a 32k backend rejects outright. Make it configurable via CLAW_MAX_READ_CHARS, defaulting to the existing 64 KB so behavior is unchanged unless set. Reads remain paged, not refused: callers still get truncated/nextOffset. 2. Compaction could not help, because it works at message granularity and an agentic turn is five messages (user / assistant+tool_use / tool_result / assistant+tool_use / tool_result). With preserve_recent_messages: 4 the only droppable message is the short user prompt, so the two oversized tool results were preserved verbatim by design. Trim preserved tool-result payloads over 16 KB to a head/tail excerpt with an explicit "[... N characters elided ...]" marker, so the model knows its view is partial and can re-read. Small payloads pass through untouched. Also apply trimming on the early-return path: a session can exceed the window while holding fewer messages than preserve_recent_messages, where should_compact is false and message-granular compaction has no move to make. compact_now no longer gates on removed_message_count alone, which would have computed the smaller session and then discarded it. Also fixes a pre-existing flaky test: repl_executes_python_code resolves the python runtime through PATH, which the PowerShell tests blank while they run. It now takes the same env_lock, so it no longer intermittently fails with "python runtime not found" on a machine that has python. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_013bVvRYn7CQKR6hT2j1L6Cs (cherry picked from commit b0d4d41e8132f8dc75717b1f74554d649639de10)