Recover from SIGWINCH without clearing the physical screen or scrollback
buffer. The startup banner and tool summary are printed before
prompt_toolkit owns the live chrome, so they live in normal terminal
scrollback. Calling erase_screen() + \x1b[3J] on every resize removed
that UI permanently — _replay_output_history cannot reconstruct it
because the banner was never added to _OUTPUT_HISTORY.
Instead, just reset prompt_toolkit's renderer cache and invalidate so
the next incremental redraw starts from a clean slate, then let the
original on_resize handler recalculate layout for the new terminal
size. This matches the behaviour of bash/zsh/fish on SIGWINCH.
FixesNousResearch/hermes-agent#22999
When auxiliary.<task> config has base_url set but api_key is empty
(common when user expects env var fallback), _resolve_task_provider_model()
returned provider="custom" with api_key=None. This caused downstream
client construction to make API calls without an Authorization header,
resulting in HTTP 401 errors.
Fix: only return "custom" when BOTH cfg_base_url AND cfg_api_key are
non-empty. When base_url is set without api_key but with a known
provider (e.g. "openrouter"), pass through to that provider so it can
resolve credentials from environment variables.
Fixes#16829
When context compression rotates the agent's session_id to a new
child session, the API server was still returning the stale parent
session_id in the X-Hermes-Session-Id response header.
This caused external clients to keep sending the old session_id,
loading uncompressed parent history instead of the compressed
continuation.
Fix: _run_agent() now includes the effective session_id in its
result dict, and the response header uses it instead of the
original provided session_id.
Sends a lightweight list_tools() probe every 3 minutes during idle
periods to prevent TCP connections from going stale behind LB / NAT
idle timeouts (commonly 300-600s). When the keepalive fails, the
reconnect event fires so the transport rebuilds the session cleanly.
Salvages the keepalive portion of @vominh1919's PR #17016. The
circuit-breaker half-open recovery from the same PR was independently
landed on main via #benbarclay's commit 8cc3cebca ("fix(mcp): add
half-open state to circuit breaker", Apr 21); only the keepalive is
salvaged here.
Fixes#17003.
The test 'test_inf_stays_string_for_integer_only' incorrectly asserted
that _coerce_number('inf') returns float('inf'), but the function
correctly returns the original string 'inf' because infinity is not
JSON-serializable.
Fixed the assertion to expect the string 'inf', and added two new tests
for negative infinity and NaN edge cases to improve coverage of the
non-JSON-serializable number guard in _coerce_number().
AnyUrl was imported inside the same try block as mcp.client.auth, so
when the mcp package was not installed, AnyUrl was undefined and
_build_client_metadata raised NameError at runtime.
Moved the AnyUrl import to its own try/except block so it's available
whenever pydantic is installed (which is a core dependency), regardless
of whether the mcp SDK is present.
Also added pytest.importorskip('mcp') to the three
test_build_client_metadata tests that exercise _build_client_metadata,
since that function depends on OAuthClientMetadata from the mcp package.
Six tests in test_bedrock_adapter.py import botocore.exceptions
directly (ConnectionClosedError, EndpointConnectionError,
ReadTimeoutError, ClientError) without guarding the import. When
botocore is not installed (it's an optional dependency), these tests
fail with ModuleNotFoundError instead of being gracefully skipped.
Added pytest.importorskip('botocore') to each affected test function,
following the same pattern used elsewhere in the test suite (e.g.
test_voice_mode.py for numpy, test_mcp_oauth.py for mcp).
Tests affected:
- TestIsStaleConnectionError: 3 tests
- TestCallConverseInvalidatesOnStaleError: 3 tests
Before: 6 FAIL with ModuleNotFoundError
After: 6 SKIP with reason message
TestTranscribeLocalExtended patches faster_whisper.WhisperModel, which
triggers an ImportError when the faster_whisper package is not installed.
Added a pytest.mark.skipif marker using importlib.util.find_spec so
these tests are gracefully skipped instead of failing with
ModuleNotFoundError.
Two defensive fixes in gateway/run.py:
1. yaml.safe_load returning None on empty config files (line 12706):
GatewayConfig.from_dict(data) crashes with AttributeError when the YAML
file is empty because safe_load returns None. All 6 other yaml.safe_load
call sites already use `or {}` — this one was missed.
Impact: gateway fails to start with empty --config file.
2. float() on env vars without ValueError guard (lines 3951, 11757, 11805,
11807): HERMES_AGENT_TIMEOUT, HERMES_AGENT_TIMEOUT_WARNING, and
HERMES_AGENT_NOTIFY_INTERVAL are cast via float() directly from
os.getenv(). A typo (e.g. "abc") raises ValueError and crashes the
agent turn or gateway startup.
Impact: single misconfigured env var crashes the entire gateway.
tar xf - -C / extracts the staging directory tree to the remote root.
GNU tar default behavior overwrites metadata (including mode) of existing
directories. When the local umask is 002 (Ubuntu default), the staging
dirs are 0775, and tar chmod's /home/<user> to 0775 — breaking sshd
StrictModes which requires 0755 or stricter for home dirs.
Add --no-overwrite-dir to the remote tar command so existing directory
metadata is preserved.
Fixes#17767
DeepSeek's /anthropic endpoint requires thinking blocks to be replayed
in multi-turn conversations for reasoning continuity. The existing code
classified api.deepseek.com as a generic third-party endpoint and stripped
ALL thinking blocks, causing HTTP 400 from DeepSeek.
Fix: add _is_deepseek_anthropic_endpoint() detector (following the Kimi
precedent) and a dedicated branch that strips only signed Anthropic blocks
while preserving unsigned ones synthesised from reasoning_content.
This follows the exact same pattern as the Kimi exemption (issue #13848)
and does not change behavior for any other third-party endpoint (Azure,
Bedrock, MiniMax, etc.).
FixesNousResearch/hermes-agent#16748
The normalize_model_name() function unconditionally converted dots to
hyphens in all model names. This caused non-Anthropic models (e.g.
gpt-5.4) to be mangled to gpt-5-4 when routed through the Anthropic
adapter path, resulting in HTTP 404 from the backend.
Now only applies dot-to-hyphen conversion for models starting with
"claude-" or "anthropic/", which are the actual Anthropic model IDs.
Fixes NousResearch/hermes-agent#17171
Related: #7421, #13061, #16417
_update_cwd() uses a bare open(self._cwd_file).read() that never
closes the file descriptor. This method runs on every terminal
command execution, so the fd leaks accumulate in long sessions.
Use a with statement so the fd is released promptly.
Fixes#15552 (standalone resubmission)
The Weixin adapter only recognized errcode=-14 as a session-expired
signal. However, iLink also returns ret=-2 with errmsg="unknown error"
for the same underlying condition (stale session). The adapter treated
ret=-2 as a rate-limit, exhausting retries with the same stale
context_token instead of refreshing the session.
Added _is_stale_session_ret() helper that distinguishes ret=-2 with
"unknown error" from genuine rate limits. Updated both the poll loop
and _send_text_chunk to use the helper.
FixesNousResearch/hermes-agent#17228
os.replace(tmp, path) replaces the symlink itself with a regular file,
breaking users who symlink config.yaml, SOUL.md, or .env from ~/.hermes/
to a dotfiles repo or managed profile package.
Fix: resolve symlinks via os.path.realpath() before os.replace(), so the
real file is overwritten in-place while the symlink survives.
Fixed in 7 files covering all os.replace call sites:
- utils.py (atomic_json_write, atomic_yaml_write — fixes save_config)
- hermes_cli/config.py (env sanitizer, save_env_value, remove_env_value)
- tools/skill_manager_tool.py (_atomic_write_text — SOUL.md writes)
- tools/memory_tool.py (memory file writes)
- tools/skills_sync.py (manifest writes)
- cron/jobs.py (job state + output file writes)
- agent/shell_hooks.py (hook file writes)
FixesNousResearch/hermes-agent#16743
`hermes claw migrate` copied OpenClaw's model setting verbatim, which
could be a display alias (e.g. "Claude Opus 4.6") instead of the actual
API ID (e.g. "claude-opus-4-6"). Hermes then sent the alias to the API,
causing HTTP 404 model not found.
Fix: look up the model string in agents.defaults.models (plural) alias
catalog. If found, use the resolved "id" field, prepending the provider
prefix if needed. If not found (already an API ID), pass through unchanged.
FixesNousResearch/hermes-agent#16745
_PROVIDER_MODELS["xai"] was pointing at model IDs the xAI direct API
no longer accepts:
- grok-4.20-reasoning
- grok-4-1-fast-reasoning
Replaced with the actual current xAI catalog IDs from models.dev
($HERMES_HOME/models_dev_cache.json, mirror of https://models.dev/api.json):
grok-4.20-0309-reasoning
grok-4.20-0309-non-reasoning
grok-4.20-multi-agent-0309
grok-4-1-fast
grok-4-1-fast-non-reasoning
grok-4-fast
grok-4-fast-non-reasoning
grok-4
grok-code-fast-1
The xAI-direct API (https://api.x.ai/v1) serves the dated IDs shown
above; the bare aliases (grok-4.20, grok-4.1-fast, etc.) are
OpenRouter/Vercel-gateway normalizations and are not accepted on
xAI-direct. Those gateways remain unaffected.
Fixes#16699
Both keys are documented in cli-config.yaml.example and read at runtime by
hermes_cli/timeouts.py (get_provider_request_timeout and get_provider_stale_timeout),
but the provider-entry validator in config.py flagged them as unknown, producing
noisy warnings on every CLI invocation for users who followed the documented config.
Fixes#16779
On macOS (bash 3.2 and some Homebrew bash builds) `source`ing a file that
contains `declare -x` statements prints each declaration to stdout. The
persistent-shell wrapper in tools/environments/base.py was only redirecting
stderr when sourcing the session snapshot, so ~60 lines of env vars leaked
into every terminal tool response — blowing out context and triggering
HTTP 400s on context-limited providers.
Fix: redirect both stdout and stderr when sourcing the snapshot. Linux
bash is silent here, so the redirect is harmless there; macOS no longer
leaks.
Closes#15459
Co-authored-by: Sanjays2402 <51058514+Sanjays2402@users.noreply.github.com>
update_model() recalculated threshold_tokens but left tail_token_budget
and max_summary_tokens at their __init__ values. When switching from a
200K model to 32K, the tail budget stayed at ~20K tokens (62% of 32K)
instead of the intended ~10%.
Adds budget recalculation in update_model() and 2 regression tests.
The least_used strategy selected entries via min(request_count) but
never incremented the counter. All entries stayed at count=0, so the
strategy degenerated to fill_first behavior with no actual load balancing.
Now increments request_count after each selection and persists the update.
vominh1919