fb0aa2e576e90b7b94c1e9f1a10b4a653ee487d1
M5a task 04 stopped twice on the chat-template tags the check refuses. The first time, the model read them in a file and took them for its own template. The second time, it spelled them out in its own reasoning. Measured on straylight: the think and tool-call tags are one token whatever the tokenizer's flag. Inside any chat message, the turn markers become control tokens, so a tool result can forge a system turn. Adds the rule to AGENTS.md, and proposes neutralizing the tags in loopd as an open decision. Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
Description
sovereign personal agent harness
4.8 MiB
Languages
Rust
97.6%
Shell
1.1%
Python
1.1%
Nix
0.2%