hermes-agent/tools
Teknium 7f1b2b4569
fix(approval): pin 'silence is not consent' contract on timeout/deny (#24912) (#30879)
User incident (Slack, 2026-05-13): user walked away mid-conversation,
agent requested approval to run `rm -rf .git`, the prompt timed out
after the gateway_timeout (default 300s), and the agent removed the
.git folder on its own. Corroborated by an independent report from a
Telegram user.

The underlying code path was correct — `check_all_command_guards`
returns `approved=False` with a BLOCKED message on both timeout and
explicit deny, and `terminal_tool` surfaces that as `status=blocked`
to the agent. The bug is at the model-interface layer: the message
"BLOCKED: Command timed out. Do NOT retry this command." reads to
some models as "try a different command achieving the same outcome."

This commit changes only the model-facing message + the structured
return shape:

  - Timeout message now explicitly names the three evasion paths the
    agent must avoid: retry, rephrase, AND achieve the same outcome
    via a different command. Ends with "Silence is not consent."
  - Explicit deny gets the same shape minus the silence-is-not-consent
    line (it WAS an explicit deny, not silence).
  - New structured fields on the return dict: `outcome` ("timeout"
    or "denied") and `user_consent` (always False on this branch)
    so plugins, hooks, and audit pipelines don't have to string-parse
    the message to distinguish the two cases.

The mechanism that should already have prevented the original incident
— timeout treated as deny, BLOCKED result, post hook fires with
`choice="timeout"` — is unchanged. This commit hardens only the
agent's reading of the result.

Tests:
  - test_timeout_returns_approved_false_with_no_consent — pins the
    return shape on the Slack-shaped notify_cb-registered path
  - test_timeout_message_is_emphatic_against_retry_and_rephrase —
    pins the exact phrases the message must contain
  - test_explicit_deny_carries_same_no_consent_shape — same contract
    on explicit /deny
  - test_timeout_emits_post_hook_with_timeout_outcome — pins the
    post_approval_response hook payload so audit plugins can act

329 approval tests passing (4 new + 325 existing).

Fixes #24912
2026-05-23 02:59:13 -07:00
..
computer_use fix(computer-use): skip capture_after when action failed (ok=False) 2026-05-22 01:19:01 -07:00
environments fix(ssh): keep bulk sync extraction scoped to .hermes 2026-05-21 19:17:51 -07:00
neutts_samples
__init__.py
ansi_strip.py
approval.py fix(approval): pin 'silence is not consent' contract on timeout/deny (#24912) (#30879) 2026-05-23 02:59:13 -07:00
binary_extensions.py
browser_camofox.py
browser_camofox_state.py
browser_cdp_tool.py
browser_dialog_tool.py
browser_supervisor.py
browser_tool.py
budget_config.py
checkpoint_manager.py
clarify_gateway.py
clarify_tool.py
code_execution_tool.py
computer_use_tool.py
credential_files.py
cronjob_tools.py
debug_helpers.py
delegate_tool.py
discord_tool.py
env_passthrough.py
fal_common.py refactor(image_gen): port FAL backend to plugins/image_gen/fal 2026-05-22 04:10:45 -07:00
feishu_doc_tool.py
feishu_drive_tool.py
file_operations.py
file_state.py
file_tools.py fix(file-safety): block auth.json read via TERMINAL_CWD relative path 2026-05-22 20:15:09 -07:00
fuzzy_match.py
homeassistant_tool.py
image_generation_tool.py refactor(image_gen): port FAL backend to plugins/image_gen/fal 2026-05-22 04:10:45 -07:00
interrupt.py
kanban_tools.py
lazy_deps.py
managed_tool_gateway.py
mcp_oauth.py fix(security): guard os.chmod(parent) against / and top-level dirs 2026-05-20 22:56:55 -07:00
mcp_oauth_manager.py
mcp_tool.py
memory_tool.py fix(memory): guard against external drift in MEMORY.md/USER.md (#26045) (#30877) 2026-05-23 02:51:29 -07:00
microsoft_graph_auth.py
microsoft_graph_client.py
mixture_of_agents_tool.py
neutts_synth.py
openrouter_client.py
osv_check.py
patch_parser.py
path_security.py
process_registry.py
registry.py
schema_sanitizer.py
send_message_tool.py Fix unsafe gateway media path delivery 2026-05-23 01:40:35 -07:00
session_search_tool.py
skill_manager_tool.py fix(skills): prune dependency/venv dirs from all skill scanners (#30042) 2026-05-21 14:18:02 -07:00
skill_provenance.py
skill_usage.py fix(skills): prune dependency/venv dirs from all skill scanners (#30042) 2026-05-21 14:18:02 -07:00
skills_guard.py fix(skills_guard): explain why --force is rejected on dangerous verdicts 2026-05-23 02:37:30 -07:00
skills_hub.py fix(skills,pairing): path traversal guard in uninstall, lock list_pending, hash file paths 2026-05-22 19:59:24 -07:00
skills_sync.py fix(skills): prune dependency/venv dirs from all skill scanners (#30042) 2026-05-21 14:18:02 -07:00
skills_tool.py fix(skills): prune dependency/venv dirs from all skill scanners (#30042) 2026-05-21 14:18:02 -07:00
slash_confirm.py
terminal_tool.py
tirith_security.py
todo_tool.py
tool_backend_helpers.py
tool_output_limits.py
tool_result_storage.py
transcription_tools.py fixup: log lazy-install errors at debug + AUTHOR_MAP for CipherFrame 2026-05-21 23:36:18 -07:00
tts_tool.py Add opt-in xAI TTS speech tag pauses 2026-05-20 09:22:28 -07:00
url_safety.py
video_generation_tool.py
vision_tools.py
voice_mode.py fix(voice): chunk oversized CLI recordings 2026-05-21 14:17:39 -07:00
web_tools.py
website_policy.py
x_search_tool.py fix(x_search): surface degraded results + validate dates 2026-05-21 02:38:45 +05:30
xai_http.py
yuanbao_tools.py Fix unsafe gateway media path delivery 2026-05-23 01:40:35 -07:00