fix(file_tools): strip ANSI escape codes from write_file and patch content#2532
Merged
fix(file_tools): strip ANSI escape codes from write_file and patch content#2532
Conversation
…ntent Models occasionally copy ANSI escape sequences from terminal output or display formatting into file content, breaking shebangs and injecting binary characters into scripts. Strip ANSI codes (CSI, OSC, simple escapes) from: - write_file content - patch old_string, new_string, and V4A patch content The check is fast (skips entirely if no ESC byte present). Reported by Andi Jaeger.
This was referenced Mar 22, 2026
teknium1
added a commit
that referenced
this pull request
Mar 23, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR #2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
teknium1
added a commit
that referenced
this pull request
Mar 23, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR #2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
InB4DevOps
pushed a commit
to InB4DevOps/hermes-agent
that referenced
this pull request
Mar 24, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR NousResearch#2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
InB4DevOps
pushed a commit
to InB4DevOps/hermes-agent
that referenced
this pull request
Mar 24, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR NousResearch#2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
InB4DevOps
pushed a commit
to InB4DevOps/hermes-agent
that referenced
this pull request
Mar 24, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR NousResearch#2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
InB4DevOps
pushed a commit
to InB4DevOps/hermes-agent
that referenced
this pull request
Mar 25, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR NousResearch#2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
outsourc-e
pushed a commit
to outsourc-e/hermes-agent
that referenced
this pull request
Mar 26, 2026
…ntent (NousResearch#2532) Models occasionally copy ANSI escape sequences from terminal output or display formatting into file content, breaking shebangs and injecting binary characters into scripts. Strip ANSI codes (CSI, OSC, simple escapes) from: - write_file content - patch old_string, new_string, and V4A patch content The check is fast (skips entirely if no ESC byte present). Reported by Andi Jaeger.
outsourc-e
pushed a commit
to outsourc-e/hermes-agent
that referenced
this pull request
Mar 26, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR NousResearch#2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
aashizpoudel
pushed a commit
to aashizpoudel/hermes-agent
that referenced
this pull request
Mar 30, 2026
…ntent (NousResearch#2532) Models occasionally copy ANSI escape sequences from terminal output or display formatting into file content, breaking shebangs and injecting binary characters into scripts. Strip ANSI codes (CSI, OSC, simple escapes) from: - write_file content - patch old_string, new_string, and V4A patch content The check is fast (skips entirely if no ESC byte present). Reported by Andi Jaeger.
aashizpoudel
pushed a commit
to aashizpoudel/hermes-agent
that referenced
this pull request
Mar 30, 2026
…es the model Root cause: terminal_tool, execute_code, and process_registry returned raw subprocess output with ANSI escape sequences intact. The model saw these in tool results and copied them into file writes. Previous fix (PR NousResearch#2532) stripped ANSI at the write point in file_tools.py, but this was a band-aid — regex on file content risks corrupting legitimate content, and doesn't prevent ANSI from wasting tokens in the model context. Source-level fix: - New tools/ansi_strip.py with comprehensive ECMA-48 regex covering CSI (incl. private-mode, colon-separated, intermediate bytes), OSC (both terminators), DCS/SOS/PM/APC strings, Fp/Fe/Fs/nF escapes, 8-bit C1 - terminal_tool.py: strip output before returning to model - code_execution_tool.py: strip stdout/stderr before returning - process_registry.py: strip output in poll/read_log/wait - file_tools.py: remove _strip_ansi band-aid (no longer needed) Verified: `ls --color=always` output returned as clean text to model, file written from that output contains zero ESC bytes.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Models occasionally copy ANSI escape sequences from terminal output or display formatting into file content when calling
write_fileorpatch. This breaks shebangs and injects binary characters into scripts.Fix: Strip ANSI escape codes (CSI, OSC, simple escapes) from:
write_filecontentpatchold_string, new_string, and V4A patch contentThe check is fast — skips entirely if no ESC byte (
\x1b) is present in the string.Reported by Andi Jaeger on X.
Test plan