fix(tool_parsing): require a pipe on the Qwen bare end marker (#5829)

The `end` branch of _QWEN_BARE_MARKER_RE had both pipes optional
(`\|?end\|?`), so it also matched a bare `end` between whitespace and
replaced it with a space. Messages containing Ruby, Lua or shell code that
closes a block with a lone `end` had those lines deleted, and ordinary prose
lost the word too.

Require at least one pipe so only real turn markers match; `|end`, `end|`,
`|end|` and `/|end|` strip exactly as before. Applied to the duplicated
pattern in static/js/chatRenderer.js as well.

Fixes #5547
This commit is contained in:
Husam
2026-08-07 20:33:14 +03:00
committed by GitHub
parent 36d4098421
commit f1e96d102e
3 changed files with 105 additions and 2 deletions
+4 -1
View File
@@ -478,7 +478,10 @@ const DSML_STRAY_RE = /<\s*\/?\s*[|]+\s*DSML\s*[|]+[^>]*>/gi;
const DSML_INVOKE_RE = /<\s*[|]+\s*DSML\s*[|]+\s*invoke\b[^>]*>[\s\S]*?(?:<\s*\/\s*[|]+\s*DSML\s*[|]+\s*invoke\s*>|$)/gi;
const RAW_OPENAI_TOOL_JSON_RE = /(?:\[\s*)?\{\s*"function"\s*:\s*\{[\s\S]*?\}\s*,\s*"id"\s*:\s*"[^"]*"\s*,\s*"type"\s*:\s*"function"\s*\}\s*\]?/gi;
const QWEN_ROLE_MARKER_RE = /<\/?\|(?:assistant|assistan|user|system|tool)\|>?|<\/\|end\|>?/gi;
const QWEN_BARE_MARKER_RE = /(?:^|[\t\r\n ])(?:\|?end\|?|\/?\|end\|)(?=[\t\r\n ]|$)|(?:^|[\t\r\n ])assistan(?:t)?(?=[\t\r\n ]|$)/gi;
// Keep in sync with _QWEN_BARE_MARKER_RE in src/tool_parsing.py. At least one
// pipe is required around `end`: with both optional (`\|?end\|?`) this also ate
// a bare `end` on its own line, breaking Ruby/Lua/shell snippets (#5547).
const QWEN_BARE_MARKER_RE = /(?:^|[\t\r\n ])(?:\/?\|end\||\|end|end\|)(?=[\t\r\n ]|$)|(?:^|[\t\r\n ])assistan(?:t)?(?=[\t\r\n ]|$)/gi;
// Self-narration about tool results (model echoing stdout/exit_code)
const TOOL_NARRATION_RE = /(?:The (?:result|output) shows?:?\s*)?-?\s*(?:stdout|stderr|exit_code):\s*.+/gi;