fix: eliminate execute_code progress spam on gateway platforms#1098
Merged
Conversation
Root cause: two issues combined to create visual spam on Telegram/Discord:
1. build_tool_preview() preserved newlines from tool arguments. A preview
like 'import os\nprint("...")' rendered as 2+ visual lines per
progress entry on messaging platforms. This affected execute_code most
(code always has newlines), but could also hit terminal, memory,
send_message, session_search, and process tools.
2. No deduplication of identical progress messages. When models iterate
with execute_code using the same boilerplate code (common pattern),
each call produced an identical progress line. 9 calls x 2 visual
lines = 18 lines of identical spam in one message bubble.
Fixes:
- Added _oneline() helper to collapse all whitespace (newlines, tabs) to
single spaces. Applied to ALL code paths in build_tool_preview() —
both the generic path and every early-return path that touches user
content (memory, session_search, send_message, process).
- Added dedup in gateway progress_callback: consecutive identical messages
are collapsed with a repeat counter, e.g. 'execute_code: ... (x9)'
instead of 9 identical lines. The send_progress_messages async loop
handles dedup tuples by updating the last progress_line in-place.
71eaf39 to
8121aef
Compare
teknium1
pushed a commit
that referenced
this pull request
Apr 22, 2026
…imeout Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of daemon reliability fixes: - Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (#1098) - Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (#1157) - Orphaned Chrome processes via process-group kill on shutdown (#1137) - Stale daemon after upgrade via .version sidecar and auto-restart (#1134) - Idle timeout not firing (sleep future recreated each loop) (#1110) - Navigation hanging on lifecycle events that never fire (#1059, #1092) - CDP attach hang on Chrome 144+ (#1133) - Windows daemon TCP bind with Hyper-V port conflicts (#1041) - Shadow DOM traversal in accessibility tree snapshots - doctor command for user self-diagnosis Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess environment so the daemon self-terminates after our configured inactivity timeout (default 300s). This is the daemon-side counterpart to the Python-side inactivity reaper — the daemon kills itself and its Chrome children when no commands arrive, preventing orphan accumulation even when the Python process dies without running atexit handlers. Addresses #7343 (daemon socket hangs, shadow DOM) and #13793 (orphan accumulation from force-killed sessions).
angelburgosrosado
pushed a commit
to angelburgosrosado/hermes-agent
that referenced
this pull request
Apr 27, 2026
…465f3702 fix: eliminate execute_code progress spam on gateway platforms
ulasbilgen
pushed a commit
to ulasbilgen/hermes-adhd-agent
that referenced
this pull request
May 1, 2026
…imeout Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of daemon reliability fixes: - Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098) - Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157) - Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137) - Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134) - Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110) - Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092) - CDP attach hang on Chrome 144+ (NousResearch#1133) - Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041) - Shadow DOM traversal in accessibility tree snapshots - doctor command for user self-diagnosis Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess environment so the daemon self-terminates after our configured inactivity timeout (default 300s). This is the daemon-side counterpart to the Python-side inactivity reaper — the daemon kills itself and its Chrome children when no commands arrive, preventing orphan accumulation even when the Python process dies without running atexit handlers. Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan accumulation from force-killed sessions).
aj-nt
pushed a commit
to aj-nt/hermes-agent
that referenced
this pull request
May 1, 2026
…imeout Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of daemon reliability fixes: - Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098) - Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157) - Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137) - Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134) - Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110) - Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092) - CDP attach hang on Chrome 144+ (NousResearch#1133) - Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041) - Shadow DOM traversal in accessibility tree snapshots - doctor command for user self-diagnosis Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess environment so the daemon self-terminates after our configured inactivity timeout (default 300s). This is the daemon-side counterpart to the Python-side inactivity reaper — the daemon kills itself and its Chrome children when no commands arrive, preventing orphan accumulation even when the Python process dies without running atexit handlers. Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan accumulation from force-killed sessions).
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…465f3702 fix: eliminate execute_code progress spam on gateway platforms
02356abc
pushed a commit
to 02356abc/hermes-agent
that referenced
this pull request
May 14, 2026
…imeout Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of daemon reliability fixes: - Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098) - Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157) - Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137) - Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134) - Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110) - Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092) - CDP attach hang on Chrome 144+ (NousResearch#1133) - Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041) - Shadow DOM traversal in accessibility tree snapshots - doctor command for user self-diagnosis Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess environment so the daemon self-terminates after our configured inactivity timeout (default 300s). This is the daemon-side counterpart to the Python-side inactivity reaper — the daemon kills itself and its Chrome children when no commands arrive, preventing orphan accumulation even when the Python process dies without running atexit handlers. Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan accumulation from force-killed sessions).
olympus-terminal
pushed a commit
to olympus-terminal/hermes-agent
that referenced
this pull request
May 16, 2026
…465f3702 fix: eliminate execute_code progress spam on gateway platforms
gweeteve
pushed a commit
to gweeteve/hermes-agent
that referenced
this pull request
Jun 2, 2026
…imeout Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of daemon reliability fixes: - Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098) - Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157) - Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137) - Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134) - Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110) - Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092) - CDP attach hang on Chrome 144+ (NousResearch#1133) - Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041) - Shadow DOM traversal in accessibility tree snapshots - doctor command for user self-diagnosis Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess environment so the daemon self-terminates after our configured inactivity timeout (default 300s). This is the daemon-side counterpart to the Python-side inactivity reaper — the daemon kills itself and its Chrome children when no commands arrive, preventing orphan accumulation even when the Python process dies without running atexit handlers. Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan accumulation from force-killed sessions).
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…465f3702 fix: eliminate execute_code progress spam on gateway platforms
Egavasyug
pushed a commit
to Egavasyug/hermes-agent
that referenced
this pull request
Jun 10, 2026
…imeout Upgrades agent-browser from 0.13.0 to 0.26.0, picking up 13 releases of daemon reliability fixes: - Daemon hang on Linux from waitpid(-1) race in SIGCHLD handler (NousResearch#1098) - Chrome killed after ~10s idle due to PR_SET_PDEATHSIG thread tracking (NousResearch#1157) - Orphaned Chrome processes via process-group kill on shutdown (NousResearch#1137) - Stale daemon after upgrade via .version sidecar and auto-restart (NousResearch#1134) - Idle timeout not firing (sleep future recreated each loop) (NousResearch#1110) - Navigation hanging on lifecycle events that never fire (NousResearch#1059, NousResearch#1092) - CDP attach hang on Chrome 144+ (NousResearch#1133) - Windows daemon TCP bind with Hyper-V port conflicts (NousResearch#1041) - Shadow DOM traversal in accessibility tree snapshots - doctor command for user self-diagnosis Also wires AGENT_BROWSER_IDLE_TIMEOUT_MS into the browser subprocess environment so the daemon self-terminates after our configured inactivity timeout (default 300s). This is the daemon-side counterpart to the Python-side inactivity reaper — the daemon kills itself and its Chrome children when no commands arrive, preventing orphan accumulation even when the Python process dies without running atexit handlers. Addresses NousResearch#7343 (daemon socket hangs, shadow DOM) and NousResearch#13793 (orphan accumulation from force-killed sessions).
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.
Problem
On Telegram/Discord/etc., execute_code tool calls produce massive visual spam — a single message bubble fills with 17+ identical lines like:
This happens because of two independent issues:
Issue 1: Newlines in previews
build_tool_preview()preserves \n characters from execute_code'scodeargument. A preview likeimport os\nprint("...")renders as 2 visual lines per progress entry on messaging platforms. Other tools (terminal, web_search, etc.) never have newlines in their primary argument, so they don't exhibit this.Issue 2: No deduplication of identical messages
In "all" mode (the default), every tool call gets a progress line — even when identical to the previous one. When models iterate with execute_code using the same boilerplate code (common pattern:
import os\nprint(...)), each call produces an identical progress line. 9 calls × 2 visual lines each = 18 lines of identical spam.Fixes
1. Collapse whitespace in
build_tool_preview()(agent/display.py)Newlines and tabs become spaces. Now:
import os print("=== Current Dir..."— one clean line.2. Dedup consecutive identical progress messages (
gateway/run.py)Track the last progress message. When the same message appears consecutively, collapse it with a repeat counter instead of adding a new line:
Before: 9 identical lines
After:
🐍 execute_code: "import os print("=== Cur..." (×9)The dedup works by sending a special
(__dedup__, msg, count)tuple through the progress queue. Thesend_progress_messagesasync loop updates the last line in-place and re-edits the Telegram message.Testing
import os\nprint(...)→import os print(...)(single line, 0 newlines)