build_environment_hints() now emits a factual block describing the
execution environment on every prompt build:
* Local backend: host OS, $HOME, and cwd — so the agent stops guessing
paths from the hostname. Windows also gets two specific callouts:
- hostname != username (prevents C:\Users\<hostname>\... bugs)
- `terminal` shells out to bash (git-bash/MSYS), not PowerShell
* Remote backend (docker/singularity/modal/daytona/ssh/vercel_sandbox):
host info is SUPPRESSED — the agent's tools can't touch the host, so
showing it is misleading. Instead we probe the backend once per
process with `uname/whoami/pwd` and cache the result. On probe
failure, fall back to a per-backend description that states only what
we know from the backend choice itself (container type + likely OS
family) without inventing user/cwd/$HOME.
Linux/Mac local users now get a small helpful 3-line host block instead
of an empty string. Zero change to the existing WSL hint paragraph.
Tests: 8 new/updated in TestEnvironmentHints, including a regression
guard that fails if a new remote backend is added without listing it in
_REMOTE_TERMINAL_BACKENDS.
Turns the existing 'all lints disabled' stance into 'exactly one lint
enabled' — PLW1514 (unspecified-encoding) catches bare open() /
read_text() / write_text() calls that default to locale encoding on
Windows (cp1252), silently corrupting non-ASCII content.
Changes:
1. pyproject.toml
- Migrate [tool.ruff] top-level select → [tool.ruff.lint].select
(deprecated config location, ruff was warning on every run)
- Add preview = true (PLW1514 is a preview rule in ruff 0.15.x)
- select = ['PLW1514'] (exactly one rule, deliberately minimal)
- per-file-ignores exempt tests/, plugins/, skills/, optional-skills/ —
those have their own conventions or intentionally exercise edge cases
2. website/scripts/extract-skills.py
- Fix 3 remaining bare opens (website/ was excluded from the main
sweep but needed for ruff check . to go green)
3. tests/test_lint_config.py (new, 5 tests)
- Guards against accidental rule removal. If someone deletes PLW1514
from the select list or disables preview mode, these tests fail
with a loud message explaining why the rule exists.
Paired with a companion commit (held locally for now, pending a token
with workflow scope) that adds a blocking ruff step to .github/workflows/
lint.yml. Without that companion commit, ruff is configured correctly
but nothing in CI enforces it yet — the advisory PR comment will still
surface new PLW1514 violations though, so authors see them.
Verified: ruff check . → exit 0, 0 violations across the repo.
Test suite: 90 passed, 14 skipped, 0 failed.
Codebase-wide fix for Python-on-Windows UTF-8 footguns, complementing
the earlier execute_code sandbox fixes (which remain load-bearing for
when the sandbox explicitly scrubs child env).
Problem: Python on Windows has two long-standing text-encoding pitfalls:
1. sys.stdout/stderr are bound to the console code page (cp1252 on
US-locale installs) — print('café') crashes with UnicodeEncodeError.
2. Subprocess children don't know to use UTF-8 unless PYTHONUTF8 and/or
PYTHONIOENCODING are set in their env — so any Python we spawn
(linters, sandbox children, delegation workers) hits the same bug.
Solution: A tiny bootstrap module (hermes_bootstrap.py) imported as the
first statement of every Hermes entry point:
- hermes_cli/main.py (hermes / hermes-agent console_script)
- run_agent.py (hermes-agent direct)
- acp_adapter/entry.py (hermes-acp)
- gateway/run.py (messaging gateway)
- batch_runner.py (parallel batch mode)
- cli.py (legacy direct-launch CLI)
On Windows, the bootstrap:
- os.environ.setdefault('PYTHONUTF8', '1') (PEP 540 UTF-8 mode)
- os.environ.setdefault('PYTHONIOENCODING', 'utf-8')
- sys.stdout/stderr/stdin.reconfigure(encoding='utf-8', errors='replace')
Children inherit the env vars → they run in UTF-8 mode.
Current process's stdio is reconfigured → print('café') works now.
On POSIX (Linux/macOS), the bootstrap is a complete no-op. We don't
touch LANG, LC_*, or anything else — users who have intentionally
configured a non-UTF-8 locale aren't affected. POSIX systems are
already UTF-8 by default in 99% of modern setups, so there's nothing
to fix.
setdefault() (not overwrite) means users who explicitly set PYTHONUTF8=0
or PYTHONIOENCODING=cp1252 in their environment are respected.
What this does NOT fix: bare open(path, 'w') calls in the *parent*
process still default to locale encoding because PYTHONUTF8 is only
read at interpreter init. A ruff PLW1514 sweep (separate follow-up)
will add explicit encoding='utf-8' at those ~219 call sites for
belt-and-suspenders.
Tests (17): 16 passed, 1 skipped on Windows.
- Windows: env vars set, stdio reconfigured, child inherits UTF-8 mode
- POSIX: complete no-op (verified on fake POSIX + skipped on real
POSIX since we don't have a Linux box in this session)
- Idempotence: multiple calls safe
- Graceful degradation: non-reconfigurable streams don't crash
- User opt-out: explicit PYTHONUTF8=0 is respected
- Load order: every entry point's FIRST top-level import is
hermes_bootstrap, enforced by an AST-level parametrized test
pyproject.toml: added hermes_bootstrap to py-modules so it ships with
pip installs.
Third Windows-specific sandbox bug (after WinError 10106 and the UTF-8
file-write bug): user scripts that print non-ASCII to stdout crash with
UnicodeEncodeError: 'charmap' codec can't encode character '\u2192'
in position N: character maps to <undefined>
Root cause: Python's sys.stdout on Windows is bound to the console code
page (cp1252 on US-locale installs) when the process is attached to a
pipe without PYTHONIOENCODING set. LLM-generated scripts routinely
print em-dashes, arrows, accented chars, and emoji — all of which cp1252
can't encode.
Fix: spawn the sandbox child with:
PYTHONIOENCODING=utf-8 # sys.stdin/stdout/stderr all UTF-8
PYTHONUTF8=1 # PEP 540 UTF-8 mode — open() defaults to UTF-8 too
PYTHONUTF8 is the belt-and-suspenders half: LLM scripts that call
open(path, 'w') without encoding= in user code will now produce UTF-8
files by default, matching what the sandbox already does for its own
staging files.
The parent side already decodes child stdout/stderr as UTF-8 with
errors='replace' (lines 1345-1347) so the end-to-end chain is clean.
On POSIX these values usually match the locale default already, so
setting them is harmless belt-and-suspenders for C/POSIX-locale
containers and minimal base images.
Tests added (4) — total file now at 28 passed, 1 skipped on Windows:
- test_popen_env_sets_pythonioencoding_utf8 (source grep)
- test_popen_env_sets_pythonutf8_mode (source grep)
- test_live_child_can_print_non_ascii (cross-platform live test)
- test_windows_child_without_utf8_env_would_fail (Windows negative
control — actually reproduces the bug without our env overrides,
proving the fix is load-bearing on this system)
test_code_execution_modes.py had two test-level failures and two
class-level stale skip reasons on this Windows-native branch:
- TestResolveChildPython::test_project_with_virtualenv_picks_venv_python
- TestResolveChildPython::test_project_prefers_virtualenv_over_conda
Both fail on Windows with OSError: [WinError 1314] — they call
pathlib.Path.symlink_to() to build a fake venv, which requires
developer mode or admin on Windows. They also assume POSIX venv
layout (bin/python) where Windows uses Scripts/python.exe. Skip
them with a specific, accurate reason.
Also updated two class-level skipif reasons that said
'execute_code is POSIX-only' — no longer true on this branch.
New reason explains it's the test infrastructure (symlinks + POSIX
venv layout) that's the blocker, not execute_code itself.
Results on Windows Python 3.11:
Before: 41 passed, 10 skipped, 2 failed
After: 43 passed, 12 skipped, 0 failed
Second Windows-specific sandbox bug (WinError 10106 was the first):
after the env-scrub fix let the child start, it immediately failed to
import hermes_tools with:
SyntaxError: (unicode error) 'utf-8' codec can't decode byte 0x97
in position 154: invalid start byte
Root cause: _execute_local wrote the generated hermes_tools.py stub and
the user's script.py via open(path, 'w') without encoding=. On Windows
the default text-mode encoding is cp1252 (system locale), which encodes
em-dashes (used in the stub's docstrings) as 0x97. Python then decodes
source files as UTF-8 (PEP 3120) on import, chokes on 0x97, and the
sandbox dies before any tool call.
Fix: pass encoding='utf-8' to all four file opens in the code_execution
path — the two staging writes in _execute_local (hermes_tools.py +
script.py) and the two RPC file-transport reads/writes in the generated
remote stub. JSON is ASCII-safe for most payloads but tool results
(terminal output, web_extract content) routinely carry non-ASCII.
Tests added (4):
- test_stub_and_script_writes_specify_utf8 — source grep guard
- test_file_rpc_stub_uses_utf8 — generated remote stub check
- test_stub_source_roundtrips_through_utf8 — concrete round-trip
- test_windows_default_encoding_would_have_failed — negative control
(skips on modern Python builds where default is already UTF-8
compatible, but retained for platforms where the regression could
return)
24/25 tests pass on Windows 3.11 (negative control skips because this
Python build handles em-dashes via cp1252 subset — the fix is still
correct, just the corruption path isn't always triggerable).
Adds TestPosixEquivalence to test_code_execution_windows_env.py. The
class pins the invariant that _scrub_child_env(env, is_windows=False)
produces byte-for-byte identical output to the pre-refactor inline
scrubber, across a matrix of:
- 2 synthetic envs (POSIX-shaped, Windows-shaped-on-POSIX)
- 3 passthrough rules (none, single-var, everything)
- 1 real-os.environ check on whatever platform runs the test
Plus a superset sanity check: is_windows=True must keep everything
is_windows=False keeps, and any extras must come from the
_WINDOWS_ESSENTIAL_ENV_VARS allowlist.
Rationale: the previous commit refactored the env-scrubbing inline
block into a helper. Future changes to that helper must not silently
regress POSIX behavior — if someone needs to change it, they update
_legacy_posix_scrubber in lockstep so the churn is visible in review.
All 21 tests in the file pass locally on Windows (pytest 9.0.3). 8 of
them are parametrized equivalence checks that run on every OS.
The sandbox's env scrubbing was dropping SYSTEMROOT, WINDIR, COMSPEC,
APPDATA, etc. On Windows this broke the child process before any RPC
could happen:
OSError: [WinError 10106] The requested service provider could not
be loaded or initialized
Python's socket module uses SYSTEMROOT to locate mswsock.dll during
Winsock initialization. Without it, socket.socket(AF_INET, SOCK_STREAM)
fails — and the existing loopback-TCP fallback for Windows couldn't work.
Fix: add a small Windows-only allowlist (_WINDOWS_ESSENTIAL_ENV_VARS)
matched by exact uppercase name, after the existing secret-substring
block. The secret block still runs first, so the allowlist cannot be
used to exfiltrate credentials. Also extract the env scrubber into a
testable helper (_scrub_child_env) that takes is_windows as a parameter,
so the logic can be unit-tested on any OS.
Live Winsock smoke test verifies that a child spawned with the scrubbed
env can now create an AF_INET socket on a real Windows host; the test
is guarded by sys.platform == 'win32' so POSIX CI stays green.
Two fixes from teknium1's next install run:
1. **npm install: "npm.ps1 cannot be loaded because running scripts is
disabled on this system."** Get-Command's default PATHEXT ordering
picked up ``npm.ps1`` (the PowerShell shim) ahead of ``npm.cmd`` (the
batch shim). Most Windows users have PowerShell's execution policy
set to Restricted or RemoteSigned, which blocks unsigned ``.ps1``
files. ``npm.cmd`` has no such restriction and works universally.
Install-NodeDeps now detects when Get-Command returned npm.ps1, looks
for a sibling npm.cmd in the same directory, and prefers it. Prints
an info line so the user sees why. Emits a warning + hint if only
npm.ps1 is available.
2. **"Launch hermes chat now? Y" crashes with "%1 is not a valid Win32
application" on Windows installs.** The setup wizard calls
``relaunch(["chat"])``; ``resolve_hermes_bin()`` returned
``sys.argv[0]`` which was ``...\\hermes_cli\\main.py`` (because hermes
was launched via ``python -m hermes_cli.main`` during setup).
On Windows, ``os.access(script.py, os.X_OK)`` returns True because
PATHEXT lists ``.py`` when the Python launcher is registered — but
``subprocess.run([script.py, ...])`` can't actually execute a ``.py``
directly. CreateProcessW needs a real PE file.
Fixed ``resolve_hermes_bin`` to reject ``.py``/``.pyc`` argv0 values
on Windows specifically. Falls through to ``shutil.which("hermes")``
(hermes.exe in the venv Scripts dir) or, as a final fallback, lets
build_relaunch_argv build ``[sys.executable, "-m", "hermes_cli.main"]``
which is bulletproof. POSIX behaviour unchanged — ``.py`` argv0 with
a shebang + chmod+x is still a valid exec target there.
3 new tests cover the Windows paths: .py argv0 + hermes.exe on PATH →
returns hermes.exe; .py argv0 + no PATH → returns None (caller uses
python -m); POSIX + executable .py → still accepted.
26 relaunch tests pass, no POSIX regressions.
teknium1 noticed execute_code was missing from his enabled tools on Windows.
Root cause: tools/code_execution_tool.py set ``SANDBOX_AVAILABLE =
sys.platform != \"win32\"`` as a module-level constant, originally because
the RPC transport required AF_UNIX. We added loopback TCP fallback for
the sandbox in commit eeb723fff (and covered it in the Windows TCP tests),
but forgot to lift the availability gate. So execute_code was still
invisible via the check_fn path on Windows.
- SANDBOX_AVAILABLE is now True unconditionally (it's still checked — a
future platform could flip it off via monkeypatch/env if needed).
- Error message when disabled no longer mentions Windows specifically,
just says 'sandbox is unavailable in this environment'.
- test_windows_returns_error updated: patches SANDBOX_AVAILABLE=False
directly (which was always its real intent) and asserts on 'unavailable'
instead of 'Windows'.
Tests: 171 code-execution + windows-compat tests pass, no regressions.
Three real bugs from teknium1's first Windows install run:
1. **MinGit has no bash.exe.** MinGit is the minimal-automation Git for Windows
distribution — it ships git.exe but deliberately strips bash and the POSIX
coreutils. Installer logged "Could not locate bash.exe" and Hermes would
fail to run any shell command. Switched to PortableGit — the full Git for
Windows minus the installer UI. PortableGit ships bash.exe at
<root>\bin\bash.exe plus sh, awk, sed, grep, curl, ssh in usr\bin\. ARM64
variant is detected separately (PortableGit-*-arm64.7z.exe). 32-bit falls
back to MinGit-32-bit with a warning (PortableGit is 64-bit only).
PortableGit ships as a 7z self-extractor (56MB vs MinGit's 38MB). We
invoke it with `-o<target> -y` to extract silently — no 7z install needed,
it's self-contained.
Updated tools/environments/local.py::_find_bash candidate order to prefer
the PortableGit layout (<root>\bin\bash.exe) with the MinGit layout
(<root>\usr\bin\bash.exe) as a fallback so existing installs keep working.
2. **os.execvp "Exec format error" on Windows.** Setup wizard's "Launch
hermes chat now? Y" called `os.execvp(["hermes", "chat"])` which on
Windows can only swap to real Win32 .exe files — chokes with OSError(8)
on .cmd batch shims and Python console-script wrappers. Added a
win32 branch in hermes_cli/relaunch.py::relaunch() that uses
subprocess.run + sys.exit — functionally identical (user sees "hermes
exited, then new hermes started") with one extra PID in play. POSIX
path is UNCHANGED — still uses os.execvp for in-place replacement.
Catches OSError in the Windows branch and surfaces a "open a new
terminal so PATH picks up, then re-run hermes" hint instead of a
cryptic traceback.
3. **npm install failures silent on Windows.** The install.ps1 was invoking
`npm install --silent 2>&1 | Out-Null` inside a try/catch. PowerShell's
try/catch does NOT trigger on non-zero process exit codes — only on
unhandled .NET exceptions — so npm failing printed a generic "npm
install failed" with zero information about WHY. The silent pipe ate
the stderr.
Rewrote Install-NodeDeps to:
- Resolve npm.cmd via Get-Command (respects PATHEXT) instead of
relying on bare `npm` name resolution.
- Use Start-Process with -PassThru to capture the actual exit code.
- Redirect stderr to a temp log and surface the first ~800 chars of
the real npm error when install fails, plus the log path for the
full text.
- Fail loudly with the right exit code instead of a misleading success.
- Bail cleanly with a helpful message when npm isn't on PATH at all.
4. **"True" printing to console after Node check.** `Test-Node` returns $true;
installer called it as a bare statement (no assignment, no cast). PowerShell
prints bare return values. Wrapped the call in `[void](Test-Node)`.
## Tests
- Added 3 new tests in tests/hermes_cli/test_relaunch.py covering the
Windows branch: subprocess is called (not execvp), child exit code
propagates, OSError surfaces a helpful message. All 23 tests pass
(20 existing + 3 new).
- 77 Windows-compat tests still pass, POSIX behaviour unchanged.
Second pass on native Windows support, driven by a systematic audit across
five areas: POSIX-only primitives (signal.SIGKILL/SIGHUP/SIGPIPE, os.WNOHANG,
os.setsid), path translation bugs (/c/Users → C:\Users), subprocess patterns
(npm.cmd batch shims, start_new_session no-op on Windows), subsystem health
(cron, gateway daemon, update flow), and module-level import guards.
Every change is platform-gated — POSIX (Linux/macOS) behaviour is preserved
bit-identical. Explicit "do no harm" test: test_posix_path_preserved_on_linux,
test_posix_noop, test_windows_detach_popen_kwargs_is_posix_equivalent_on_posix.
## New module
- hermes_cli/_subprocess_compat.py — shared helpers (resolve_node_command,
windows_detach_flags, windows_hide_flags, windows_detach_popen_kwargs).
All no-ops on non-Windows.
## CRITICAL fixes (would crash or silently break on Windows)
- tui_gateway/entry.py: SIGPIPE/SIGHUP referenced at module top level would
AttributeError on import on Windows, breaking `hermes --tui` entirely (it
spawns this module as a subprocess). Guard each signal.signal() call with
hasattr() and add SIGBREAK as Windows' SIGHUP equivalent.
- hermes_cli/kanban_db.py: os.waitpid(-1, os.WNOHANG) in dispatcher tick was
unguarded. os.WNOHANG doesn't exist on Windows. Gate the whole reap loop
behind `os.name != "nt"` — Windows has no zombies anyway.
- tools/code_execution_tool.py: AF_UNIX socket for execute_code RPC fails on
most Windows builds. Fall back to loopback TCP (AF_INET on 127.0.0.1:0
ephemeral port) when _IS_WINDOWS. HERMES_RPC_SOCKET env var now accepts
either a filesystem path (POSIX) or `tcp://127.0.0.1:<port>` (Windows).
Generated sandbox client parses both.
- cron/scheduler.py: `argv = ["/bin/bash", str(path)]` hardcoded. Use
shutil.which("bash") so Windows (Git Bash via MinGit) works, with a
readable error when bash is genuinely absent.
- 6 bare npm/npx spawn sites: tools_config.py x2, doctor.py, whatsapp.py
(npm install + node version probe), browser_tool.py x2. On Windows npm
is npm.cmd / npx is npx.cmd (batch shims); subprocess.Popen(["npm", ...])
fails with WinError 193. shutil.which(...) returns the absolute .cmd
path which CreateProcessW accepts because the extension routes through
cmd.exe /c. POSIX behaviour unchanged (shutil.which still returns the
same path subprocess would resolve itself).
## HIGH fixes (silent misbehaviour on Windows)
- tools/environments/local.py get_temp_dir: hardcoded /tmp returned on
Windows meant `_cwd_file = "/tmp/hermes-cwd-*.txt"`, which bash wrote
via MSYS2's virtual /tmp but native Python couldn't open. Result: cwd
tracking silently broken — `cd` in terminal tool did nothing. Windows
branch now returns `%HERMES_HOME%/cache/terminal` with forward slashes
(works in both bash and Python, guaranteed no spaces).
- tools/environments/local.py _make_run_env PATH injection: `/usr/bin not
in split(":")` heuristic mangles Windows PATH (";" separator). Gate
the injection behind `not _IS_WINDOWS`.
- hermes_cli/gateway.py launch_detached_profile_gateway_restart: outer
Popen + watcher-script Popen both used start_new_session=True, which
Windows silently ignores. Watcher stayed attached to CLI's console,
died when user closed terminal after `hermes update`, left gateway
stale. Now branches through windows_detach_popen_kwargs() helper
(CREATE_NEW_PROCESS_GROUP | DETACHED_PROCESS | CREATE_NO_WINDOW on
Windows, start_new_session=True on POSIX — identical to main).
## MEDIUM fixes
- gateway/run.py /restart and /update handlers: hardcoded bash/setsid
chain crashes on Windows when user triggers /update in-gateway. Now
has sys.platform=="win32" branch using sys.executable + a tiny
Python watcher with proper detach flags. POSIX path is unchanged.
- cli.py _git_repo_root: Git on Windows sometimes returns /c/Users/...
style paths that break subprocess.Popen(cwd=...) and Path().resolve().
Added _normalize_git_bash_path() helper that translates /c/Users,
/cygdrive/c, /mnt/c variants to native C:\Users form. POSIX no-op.
_git_repo_root() now routes every result through it.
- cli.py worktree .worktreeinclude: os.symlink on directories failed
hard on Windows (requires admin or Developer Mode). Falls back to
shutil.copytree with a warning log.
## Tests
- 29 new tests in tests/tools/test_windows_native_support.py covering:
subprocess_compat helpers, TUI entry signal guards, kanban waitpid
guard, code_execution TCP fallback source-level invariants, cron bash
resolution, npm/npx bare-spawn lint per-file, local env Windows temp
dir, PATH injection gating, git bash path normalization, symlink
fallback, gateway detached watcher flags.
- One existing test assertion adjusted in test_browser_homebrew_paths:
it compared captured Popen argv to the BARE `"npx"` literal; after the
shutil.which() change argv[0] is the absolute path. New assertion
checks the shape (two items, second is `agent-browser`) rather than
the exact first-item string. Behaviour unchanged; test was too strict.
All 56 tests pass on Linux (30 from previous commits + 26 new).
267 tests from the affected files/dirs (browser, code_exec, local_env,
process_registry, kanban_db, windows_compat) all pass — zero regressions.
tests/hermes_cli/ (3909 pass) and tests/gateway/ (5021 pass) unchanged;
all pre-existing test failures confirmed unrelated via `git stash` re-run.
## What's still deferred (LOW priority)
- Visible cmd-window flashes on short-lived console apps (~14 sites) —
cosmetic, needs a follow-up pass once we have user reports.
- agent/file_safety.py POSIX-only security deny patterns — separate
hardening task.
- tools/process_registry.py returning "/tmp" as fallback — theoretical;
reachable only when all env-var candidates fail.
Pre-existing Windows bug surfaced while reviewing the portable-MinGit
install: prompt_toolkit's Buffer.open_in_editor() falls back to POSIX
absolute paths (/usr/bin/nano, /usr/bin/vi, /usr/bin/emacs) that don't
exist on native Windows. When neither $EDITOR nor $VISUAL is set,
Ctrl+X Ctrl+E ("open prompt in editor") and /edit both silently do
nothing on Windows — the user hits the key, nothing happens, no error.
This wasn't caused by MinGit (full Git for Windows doesn't fix it either,
because the Windows Python subprocess call resolves `/usr/bin/nano` as
`C:\usr\bin\nano`, which doesn't exist even with nano installed).
Fixes:
- hermes_cli/stdio.py::configure_windows_stdio now sets EDITOR=notepad
on Windows if neither EDITOR nor VISUAL is set. notepad.exe is in
every Windows install, works as a blocking editor (subprocess.call
waits for the window to close), and writes back to the file.
- hermes_cli/config.py (hermes config edit): reorder fallback list so
Windows tries notepad first — previously nano led the list, which
required Git Bash / WSL to be in PATH.
- Users who want VSCode / Neovim / Notepad++ can still override via
$env:EDITOR — that's checked before our default kicks in. Docstring
spells out the common overrides.
The Ink TUI (`hermes --tui`) already handled Windows correctly via
ui-tui/src/lib/editor.ts falling back to notepad.exe on win32 — this
commit brings the classic prompt_toolkit CLI into parity.
3 new tests in test_windows_native_support.py verify:
- EDITOR=notepad gets set when unset on Windows
- Explicit $EDITOR is respected
- $VISUAL is respected (not overwritten by our default)
Native Windows (with Git for Windows installed) can now run the Hermes CLI
and gateway end-to-end without crashing. install.ps1 already existed and
the Git Bash terminal backend was already wired up — this PR fills the
remaining gaps discovered by auditing every Windows-unsafe primitive
(`signal.SIGKILL`, `os.kill(pid, 0)` probes, bare `fcntl`/`termios`
imports) and by comparing hermes against how Claude Code, OpenCode, Codex,
and Cline handle native Windows.
## What changed
### UTF-8 stdio (new module)
- `hermes_cli/stdio.py` — single `configure_windows_stdio()` entry point.
Flips the console code page to CP_UTF8 (65001), reconfigures
`sys.stdout`/`stderr`/`stdin` to UTF-8, sets `PYTHONIOENCODING` + `PYTHONUTF8`
for subprocesses. No-op on non-Windows. Opt out via `HERMES_DISABLE_WINDOWS_UTF8=1`.
- Called early in `cli.py::main`, `hermes_cli/main.py::main`, and
`gateway/run.py::main` so Unicode banners (box-drawing, geometric
symbols, non-Latin chat text) don't `UnicodeEncodeError` on cp1252
consoles.
### Crash sites fixed
- `hermes_cli/main.py:7970` (hermes update → stuck gateway sweep): raw
`os.kill(pid, _signal.SIGKILL)` → `gateway.status.terminate_pid(pid, force=True)`
which routes through `taskkill /T /F` on Windows.
- `hermes_cli/profiles.py::_stop_gateway_process`: same fix — also
converted SIGTERM path to `terminate_pid()` and widened OSError catch
on the intermediate `os.kill(pid, 0)` probe.
- `hermes_cli/kanban_db.py:2914, 3041`: raw `signal.SIGKILL` →
`getattr(signal, "SIGKILL", signal.SIGTERM)` fallback (matches the
pattern already used in `gateway/status.py`).
### OSError widening on `os.kill(pid, 0)` probes
Windows raises `OSError` (WinError 87) for a gone PID instead of
`ProcessLookupError`. Widened the catch at:
- `gateway/run.py:15101` (`--replace` wait-for-exit loop — without this,
the loop busy-spins the full 10s every Windows gateway start)
- `hermes_cli/gateway.py:228, 460, 940`
- `hermes_cli/profiles.py:777`
- `tools/process_registry.py::_is_host_pid_alive`
- `tools/browser_tool.py:1170, 1206`
### Dashboard PTY graceful degradation
`hermes_cli/pty_bridge.py` depends on `fcntl`/`termios`/`ptyprocess`,
none of which exist on native Windows. Previously a Windows dashboard
would crash on `import hermes_cli.web_server` because of a top-level
import. Now:
- `hermes_cli/web_server.py` wraps the pty_bridge import in
`try/except ImportError` and sets `_PTY_BRIDGE_AVAILABLE=False`.
- The `/api/pty` WebSocket handler returns a friendly "use WSL2 for
this tab" message instead of exploding.
- Every other dashboard feature (sessions, jobs, metrics, config
editor) runs natively on Windows.
### Dependency
- `pyproject.toml`: add `tzdata>=2023.3; sys_platform == 'win32'` so
Python's `zoneinfo` works on Windows (which has no IANA tzdata
shipped with the OS). Credits @sprmn24 (PR #13182).
### Docs
- README.md: removed "Native Windows is not supported"; added
PowerShell one-liner and Git-for-Windows prerequisite note.
- `website/docs/getting-started/installation.md`: new Windows section
with capability matrix (everything native except the dashboard
`/chat` PTY tab, which is WSL2-only).
- `website/docs/user-guide/windows-wsl-quickstart.md`: reframed as
"WSL2 as an alternative to native" rather than "the only way".
- `website/docs/developer-guide/contributing.md`: updated
cross-platform guidance with the `signal.SIGKILL` / `OSError`
rules we enforce now.
- `website/docs/user-guide/features/web-dashboard.md`: acknowledged
native Windows works for everything except the embedded PTY pane.
## Why this shape
Pulled from a survey of how other agent codebases handle native
Windows (Claude Code, OpenCode, Codex, Cline):
- All four treat Git Bash as the canonical shell on Windows, same as
hermes already does in `tools/environments/local.py::_find_bash()`.
- None of them force `SetConsoleOutputCP` — but they don't have to,
Node/Rust write UTF-16 to the Win32 console API. Python does not get
that for free, so we flip CP_UTF8 via ctypes.
- None of them ship PowerShell-as-primary-shell (Claude Code exposes
PS as a secondary tool; scope creep for this PR).
- All of them use `taskkill /T /F` for force-kill on Windows, which
is exactly what `gateway.status.terminate_pid(force=True)` does.
## Non-goals (deliberate scope limits)
- No PowerShell-as-a-second-shell tool — worth designing separately.
- No terminal routing rewrite (#12317, #15461, #19800 cluster) — that's
the hardest design call and needs a separate doc.
- No wholesale `open()` → `open(..., encoding="utf-8")` sweep (Tianworld
cluster) — will do as follow-up if users hit actual breakage; most
modern code already specifies it.
## Validation
- 28 new tests in `tests/tools/test_windows_native_support.py` — all
platform-mocked, pass on Linux CI. Cover:
- `configure_windows_stdio` idempotency, opt-out, env-preservation
- `terminate_pid` taskkill routing, failure → OSError, FileNotFoundError fallback
- `getattr(signal, "SIGKILL", …)` fallback shape
- `_is_host_pid_alive` OSError widening (Windows-gone-PID behavior)
- Source-level checks that all entry points call `configure_windows_stdio`
- pty_bridge import-guard present in `web_server.py`
- README no longer says "not supported"
- 12 pre-existing tests in `tests/tools/test_windows_compat.py` still pass.
- `tests/hermes_cli/` ran fully (3909 passed, 9 failures — all confirmed
pre-existing on main by stash-test).
- `tests/gateway/` ran fully (5021 passed, 1 pre-existing failure).
- `tests/tools/test_process_registry.py` + `test_browser_*` pass.
- Manual smoke: `import hermes_cli.stdio; import gateway.run;
import hermes_cli.web_server` — all clean, `_PTY_BRIDGE_AVAILABLE=True`
on Linux (as expected).
## Files
- New: `hermes_cli/stdio.py`, `tests/tools/test_windows_native_support.py`
- Modified: `cli.py`, `gateway/run.py`, `hermes_cli/main.py`,
`hermes_cli/profiles.py`, `hermes_cli/gateway.py`,
`hermes_cli/kanban_db.py`, `hermes_cli/pty_bridge.py`,
`hermes_cli/web_server.py`, `tools/browser_tool.py`,
`tools/process_registry.py`, `pyproject.toml`, `README.md`, and 4
docs pages.
Credits to everyone whose prior PR work informed these fixes — see
the co-author trailers. All of the PRs listed in
`~/.hermes/plans/windows-support-prs.md` fixing `os.kill` / `signal.SIGKILL`
/ UTF-8 stdio / tzdata / README patterns found the same issues; this PR
consolidates them.
Co-authored-by: Philip D'Souza <9472774+PhilipAD@users.noreply.github.com>
Co-authored-by: Arecanon <42595053+ArecaNon@users.noreply.github.com>
Co-authored-by: XiaoXiao0221 <263113677+XiaoXiao0221@users.noreply.github.com>
Co-authored-by: Lars Hagen <1360677+lars-hagen@users.noreply.github.com>
Co-authored-by: Luan Dias <65574834+luandiasrj@users.noreply.github.com>
Co-authored-by: Ruzzgar <ruzzgarcn@gmail.com>
Co-authored-by: sprmn24 <oncuevtv@gmail.com>
Co-authored-by: adybag14-cyber <252811164+adybag14-cyber@users.noreply.github.com>
Co-authored-by: Prasanna28Devadiga <54196612+Prasanna28Devadiga@users.noreply.github.com>
test_build_pipeline_runtime_reuses_existing_teams_adapter_surface set
delivery_mode='incoming_webhook' but omitted incoming_webhook_url.
_teams_delivery_is_configured() requires the URL to mark delivery as
enabled, so the guarded build_pipeline_runtime gate in runtime.py
correctly left teams_sender=None and the assertion failed.
The intent of the test — prove we reuse the existing TeamsSummaryWriter
from plugins/platforms/teams/adapter.py rather than introducing a new
adapter surface elsewhere — is unchanged. Added the URL so the gate
passes and the architectural assertion holds.
Two salvage follow-ups on top of @dlkakbs's plugin runtime.
1. Install a drop-scheduler when the runtime fails to build.
Previously when ``build_pipeline_runtime()`` raised (e.g. missing
Graph env vars, subscription store path unwritable), ``bind_gateway_runtime``
logged a warning and returned False, leaving the msgraph_webhook
adapter with no scheduler at all. Incoming Graph notifications
would then fall back to the adapter's default ``handle_message``
path, which produces a raw JSON dump as a user-role message — not
useful and fires every time Graph retries.
Now a no-op drop-scheduler is installed instead, so:
- Graph notifications ack cleanly (202) so Graph stops retrying.
- The failure is surfaced once in the log with the error.
- No user-role messages get manufactured from raw change payloads.
The adapter is still bindable later once the runtime becomes
available (e.g. after the operator runs ``hermes teams-pipeline
validate`` and fixes the config), since the gateway's
``_teams_pipeline_runtime`` sentinel wasn't set to a non-None value.
2. Test wiring for ``_teams_pipeline_plugin_enabled()`` gate.
The happy-path runner-wiring tests monkeypatched ``bind_gateway_runtime``
but not ``_load_gateway_config``. In the hermetic test environment
the real config read ran, saw no enabled plugins, and short-circuited
the bind call before the test could observe it — so the test
expected ``calls == [runner]`` but got ``calls == []``.
Adds a ``_load_gateway_config`` monkeypatch with
``plugins.enabled = ["teams_pipeline"]`` to the happy-path tests.
The explicit-disabled test ``test_gateway_runner_skips_wiring_when_teams_pipeline_plugin_disabled``
already patches the config correctly.
Also renames ``test_bind_gateway_runtime_leaves_scheduler_unchanged_on_failure``
to ``test_bind_gateway_runtime_installs_drop_scheduler_on_failure``
and updates the assertion — this test contradicted the drop-scheduler
test in ``tests/plugins/test_teams_pipeline_plugin.py`` which
expected the scheduler to be installed. The plugin-test name
(``test_bind_gateway_runtime_drops_notifications_when_unavailable``)
clearly describes the intended behavior; fixing the wiring-test
assertion aligns both tests.
Validation:
- ``scripts/run_tests.sh tests/plugins/test_teams_pipeline_plugin.py
tests/gateway/test_teams_pipeline_runtime_wiring.py
tests/hermes_cli/test_teams_pipeline_plugin_cli.py`` — 25/25 passed.
Third slice of the Microsoft Teams meeting pipeline stack, salvaged
onto current main. Adds the standalone teams_pipeline plugin that
consumes Graph change notifications from the webhook listener,
resolves meeting artifacts (transcript first, recording + STT fallback
later), persists job state in a durable store, and exposes an operator
CLI for inspection, replay, subscription management, and validation.
Design choices follow maintainer review feedback on PR #19815:
- Standalone plugin rather than bolted-on core surface
(plugins/teams_pipeline/, kind: standalone in plugin.yaml).
- Zero new model tools. The agent drives the pipeline by invoking
the operator CLI via the terminal tool, guided by the skill that
ships with a follow-up PR.
- Reuses the existing msgraph_webhook gateway platform for Graph
ingress. Pipeline runtime is wired in via bind_gateway_runtime and
gated on plugins.enabled so gateways that don't run the plugin
boot cleanly.
Additions:
- plugins/teams_pipeline/: runtime (gateway wiring + config builder),
pipeline core, durable SQLite store, subscription maintenance
helpers, Graph artifact resolution, operator CLI (list, show,
run/replay, fetch dry-run, subscriptions list, subscribe,
renew-subscription, delete-subscription, maintain-subscriptions,
token-health, validate).
- hermes_cli/main.py: second-pass plugin CLI discovery so any
standalone plugin registered via ctx.register_cli_command()
outside the memory-plugin convention path gets its subcommand
wired into argparse without touching core.
- gateway/run.py: _teams_pipeline_plugin_enabled() config gate,
_wire_teams_pipeline_runtime() binding after adapter setup, and
the two runner attributes used by the runtime.
Credit to @dlkakbs for the entire plugin implementation.
Follow-up to #15328's vision-unsupported retry branch in run_agent.py.
_strip_images_from_messages() previously deleted any message whose content
was entirely images. That's fine for synthetic user messages injected for
attachment delivery, but it breaks providers for tool-role messages — the
paired tool_call_id on the preceding assistant message ends up unmatched,
which OpenAI-compatible APIs reject with HTTP 400.
Fix: tool-role messages whose content becomes empty are replaced with a
plaintext placeholder that preserves the tool_call_id linkage. Only
non-tool messages are dropped. Added 10 tests covering the role-alternation
invariants + image-type coverage.
Image-rejection detector: expanded phrase list (image content not
supported / multimodal input / vision input / model does not support
image) and gated on 4xx status so transient 5xx errors never get
misinterpreted as 'server said no to images'. Detection is documented as
best-effort English phrase matching.
AUTHOR_MAP: mapped 3820588+ddupont808@users.noreply.github.com to
ddupont808 so release notes attribute the salvage correctly.
Background macOS desktop control via cua-driver MCP — does NOT steal the
user's cursor or keyboard focus, works with any tool-capable model.
Replaces the Anthropic-native `computer_20251124` approach from the
abandoned #4562 with a generic OpenAI function-calling schema plus SOM
(set-of-mark) captures so Claude, GPT, Gemini, and open models can all
drive the desktop via numbered element indices.
- `tools/computer_use/` package — swappable ComputerUseBackend ABC +
CuaDriverBackend (stdio MCP client to trycua/cua's cua-driver binary).
- Universal `computer_use` tool with one schema for all providers.
Actions: capture (som/vision/ax), click, double_click, right_click,
middle_click, drag, scroll, type, key, wait, list_apps, focus_app.
- Multimodal tool-result envelope (`_multimodal=True`, OpenAI-style
`content: [text, image_url]` parts) that flows through
handle_function_call into the tool message. Anthropic adapter converts
into native `tool_result` image blocks; OpenAI-compatible providers
get the parts list directly.
- Image eviction in convert_messages_to_anthropic: only the 3 most
recent screenshots carry real image data; older ones become text
placeholders to cap per-turn token cost.
- Context compressor image pruning: old multimodal tool results have
their image parts stripped instead of being skipped.
- Image-aware token estimation: each image counts as a flat 1500 tokens
instead of its base64 char length (~1MB would have registered as
~250K tokens before).
- COMPUTER_USE_GUIDANCE system-prompt block — injected when the toolset
is active.
- Session DB persistence strips base64 from multimodal tool messages.
- Trajectory saver normalises multimodal messages to text-only.
- `hermes tools` post-setup installs cua-driver via the upstream script
and prints permission-grant instructions.
- CLI approval callback wired so destructive computer_use actions go
through the same prompt_toolkit approval dialog as terminal commands.
- Hard safety guards at the tool level: blocked type patterns
(curl|bash, sudo rm -rf, fork bomb), blocked key combos (empty trash,
force delete, lock screen, log out).
- Skill `apple/macos-computer-use/SKILL.md` — universal (model-agnostic)
workflow guide.
- Docs: `user-guide/features/computer-use.md` plus reference catalog
entries.
44 new tests in tests/tools/test_computer_use.py covering schema
shape (universal, not Anthropic-native), dispatch routing, safety
guards, multimodal envelope, Anthropic adapter conversion, screenshot
eviction, context compressor pruning, image-aware token estimation,
run_agent helpers, and universality guarantees.
469/469 pass across tests/tools/test_computer_use.py + the affected
agent/ test suites.
- `model_tools.py` provider-gating: the tool is available to every
provider. Providers without multi-part tool message support will see
text-only tool results (graceful degradation via `text_summary`).
- Anthropic server-side `clear_tool_uses_20250919` — deferred;
client-side eviction + compressor pruning cover the same cost ceiling
without a beta header.
- macOS only. cua-driver uses private SkyLight SPIs
(SLEventPostToPid, SLPSPostEventRecordTo,
_AXObserverAddNotificationAndCheckRemote) that can break on any macOS
update. Pin with HERMES_CUA_DRIVER_VERSION.
- Requires Accessibility + Screen Recording permissions — the post-setup
prints the Settings path.
Supersedes PR #4562 (pyautogui/Quartz foreground backend, Anthropic-
native schema). Credit @0xbyt4 for the original #3816 groundwork whose
context/eviction/token design is preserved here in generic form.
Defense-in-depth polish on top of the webhook listener before it becomes
a real attack surface once the pipeline starts creating subscriptions
and Graph starts POSTing to the configured public URL.
- Timing-safe clientState comparison. Previously used `==` on strings;
switches to hmac.compare_digest so a mismatch does not leak how many
leading characters matched. client_state is documented as a strong
shared secret (openssl rand -hex 32 in the setup docs), so a
timing-safe primitive is the right call.
- Split GET and POST handlers. Graph validates a subscription by sending
GET with validationToken in the query; anything else on GET is now a
400 so the endpoint cannot be probed or mistakenly used for data
exfil. Previously a bare GET fell through to the POST path and blew
up on request.json() with a confusing 400.
- Empty response bodies on success. 202 is returned with no body so
internal counters (accepted / duplicates / scheduled) do not leak to
any caller that can reach the endpoint; counters remain observable
via /health for operators. 403 on every-item-bad-clientState batches
(so forged POSTs stop retrying), 400 on malformed / unknown-resource
batches (sender configuration issue).
- Optional source-IP allowlist. New `allowed_source_cidrs` extra field
(list or comma-separated string) and `MSGRAPH_WEBHOOK_ALLOWED_SOURCE_CIDRS`
env var let operators restrict the webhook to Microsoft Graph's
published webhook source ranges in production. Empty = allow all,
preserving dev-tunnel / localhost workflows. Invalid CIDRs are
logged and ignored rather than crashing. Also gates the handshake
endpoint so disallowed IPs cannot probe it.
- Tests updated for the new response contract (empty-body 202,
auth-only 403, config-error 400) and extended to cover: bare GET
rejection, POST-with-validationToken handshake tolerance,
timing-safe compare actually invoked via hmac.compare_digest spy,
malformed body / missing value array, IP allowlist accept/reject
paths, handshake IP allowlist, invalid CIDR entries, comma-string
CIDR list parsing. 52/52 passed (was 40).
Full gateway suite: 5049 passed / 1 pre-existing failure in
test_discord_free_response (unrelated, reproduces on clean origin/main).
* feat(profile): shareable profile distributions (pack/install/update/info)
Closes#20456.
Turns a profile into a portable, versioned artifact. Packs SOUL.md, config,
skills, cron, and an env-var manifest into a tar.gz that others can install
from a local path, URL, or git repo. Updates re-pull the distribution while
preserving user data (memories, sessions, auth.json, .env) and the user's
config.yaml overrides.
New subcommands (under hermes profile, no parallel tree):
hermes profile pack <name> [-o FILE]
hermes profile install <source> [--name N] [--alias] [--force] [-y]
hermes profile update <name> [--force-config] [-y]
hermes profile info <name>
Manifest (distribution.yaml at the profile root): name, version,
hermes_requires, author, env_requires, distribution_owned.
Security:
- Installer shows manifest + env-var requirements before mutating disk;
confirmation required unless -y.
- auth.json and .env are never packed (same exclude set as profile export).
- Cron jobs are packed but NOT auto-scheduled — user is pointed at
'hermes -p <name> cron list' to review.
- Archive extraction rejects path traversal (../ members).
- Alias creation is opt-in via --alias.
Update semantics:
- Distribution-owned paths (SOUL.md, skills/, cron/, mcp.json, manifest):
replaced from the new archive.
- config.yaml: preserved by default; --force-config to overwrite.
- User-owned paths (memories/, sessions/, auth.json, .env, state.db*,
logs/, workspace/, plans/, home/, *_cache/, local/): never touched.
Version pin:
hermes_requires accepts >=, <=, ==, !=, >, < or a bare version (treated
as >=). Install fails with a clear error when the running Hermes version
doesn't satisfy the spec.
Sources supported by 'install':
- Local .tar.gz / .tgz archive
- Local directory
- HTTP(S) URL pointing to a .tar.gz (uses httpx, already a dep)
- Git URL (github.com/user/repo, https://..., git@..., ssh://, git://)
Tests: 43 new unit tests (manifest parsing, version checks, env template,
pack/install/update round-trip, config-preservation, security).
E2E validated via real CLI invocations against an isolated HERMES_HOME
covering pack, install with confirmation, update preservation, update
--force-config, decline-preview, duplicate-install rejection, and
version-requirement rejection.
* refactor(profile-dist): git-only — drop tar.gz/HTTP transports and pack
Scope-cut on top of the original distribution PR: a profile distribution
is now exclusively a git repository (or a local directory during
development). The tar.gz / HTTP archive transports and the matching
`hermes profile pack` subcommand have been removed.
Why:
* GitHub tags, branches, and commits are already the right versioning
primitive. Tag pushes do for us what 'pack + upload' did.
* `hermes profile export` / `import` already cover local backup and
restore; they are not a distribution format and stay untouched.
* One transport means one install/update code path, one doc page,
and one mental model. The extra source types doubled the surface
for no real user win — GitHub auto-attaches release tarballs, and
`git bundle` / `git clone --mirror` cover the airgap case.
Changes:
* hermes_cli/profile_distribution.py — removed pack_profile,
_fetch_tar_archive (_http_fetch), _safe_extract, _archive_roots,
_safe_parts, _find_dist_root, tarfile/io/urlparse imports. The
new _stage_source has two arms: git URL → clone, local directory
→ use in place.
* hermes_cli/main.py — removed the 'pack' subparser and action
handler. Install help text updated to match the reduced source list.
* tests/hermes_cli/test_profile_distribution.py — rewritten around a
local-directory staging fixture. The install/update/describe suites
now build a distribution tree on disk directly and install from it,
which is what a real git clone produces after .git is stripped.
Dropped TestPack, TestFindDistRoot, and the tar-specific security
test. New tests cover _looks_like_git_url, env_example emission,
hermes_requires enforcement, and 'installer does not import
credentials if an author mistakenly leaks them in the staging tree'.
* website/docs/reference/profile-commands.md — 'Distribution commands'
section rewritten around git. Added a 'Publishing a distribution'
section. export/import stay documented as local backup/restore.
* website/docs/reference/cli-commands.md — dropped 'pack' from the
profile subcommand table.
* website/package.json — 'lint:diagrams' now passes
--exclude-code-blocks to ascii-guard. Without it, markdown tables
and box-drawing diagrams inside fenced code blocks were being
misidentified as malformed ASCII boxes, blocking the PR's
docs-site-checks CI with 8 false-positive errors.
Validation:
* Targeted suite: tests/hermes_cli/test_profile_distribution.py —
56/56 pass (down from 43 — reorganized to cover the new
local-dir paths).
* Regression: test_profiles.py + test_profile_export_credentials.py
102/102 still pass. export/import behaviour unchanged.
* Docs lint: ascii-guard lint --exclude-code-blocks docs returns
0 errors (was 8 on the PR before the flag bump).
* E2E: ran the real `hermes profile install`/`info` against a
local staging dir under an isolated HERMES_HOME — install writes
SOUL.md + skills to the target profile, info reads the manifest
back, a bogus source produces a clear error, and `hermes profile
pack` is now rejected by argparse as expected.
* feat(profile-dist): distribution-aware list/show/delete + installed_at + env preview
Polish pass on top of the git-only scope cut. Five additions, all small,
wiring into existing commands rather than adding new surface.
1. `installed_at` timestamp on the manifest
* Stamped automatically inside plan_install() on both fresh install
and update — ISO-8601 UTC, seconds resolution.
* Surfaced in `hermes profile info` as `Installed: <ts>`.
* Lets users tell "installed 6 months ago, needs update" from
"installed yesterday" without guessing from file mtimes.
2. `hermes profile list` grows a `Distribution` column
* Plain profiles: "—"
* Distribution profiles: "<name>@<version>" (e.g. `telemetry@1.2.3`)
* ProfileInfo gains three optional fields — distribution_name,
distribution_version, distribution_source — populated by a new
_read_distribution_meta() helper that swallows manifest read errors
so a broken distribution.yaml in one profile can't break `list`
for the others.
3. `hermes profile show` and `hermes profile delete` surface
distribution provenance
* show: `Distribution: name@version` + `Installed from: <source>`
plus a pointer to `hermes profile info <name>` for the full
manifest.
* delete: same lines in the pre-confirmation preview, so a user
deleting "telemetry" can see it came from
`github.com/kyle/telemetry-distribution` before they type
`telemetry` to confirm. No change to the confirmation gate itself —
deletion semantics are identical to plain profiles.
4. Install preview checks env vars against the current environment
* Replaces the "Env vars you'll need to set:" header with a simpler
"Env vars:" block.
* Each required var is labeled:
- `✓ set` — already in `os.environ` OR present as a key in the
target profile's existing .env (update case).
- `needs setting` — required but not found in either place.
- `—` — optional.
* Mirrors pip's "Requirement already satisfied" UX: no unnecessary
nagging about keys the user already has configured.
5. Docs: private distributions
* New "Private distributions" section in
website/docs/reference/profile-commands.md explaining that we
shell out to the user's `git` binary, so SSH keys / credential
helpers / GitHub CLI stored creds all work transparently. One
paragraph, two examples.
* `hermes profile info` section updated to mention `Installed:`.
Module-level hoist:
* `from datetime import datetime, timezone` was previously lazy-imported
inside plan_install(). Hoisted to module scope so tests can monkeypatch
`hermes_cli.profile_distribution.datetime` to freeze time.
Tests (+7):
* TestInstalledAtStamp.test_install_stamps_installed_at — format check
(4-digit year, 'T', +00:00 suffix).
* TestInstalledAtStamp.test_update_refreshes_installed_at — freezes
datetime.now() to 2099-01-01 and confirms update writes a new stamp.
* TestProfileInfoDistribution.test_installed_distribution_shows_in_list
— ProfileInfo.distribution_{name,version,source} populated after install.
* TestProfileInfoDistribution.test_plain_profile_has_no_distribution_fields
— plain profiles have None.
* TestProfileInfoDistribution.test_malformed_manifest_does_not_break_list
— broken distribution.yaml in one profile doesn't break list_profiles().
Validation:
* 163/163 tests pass (56 distribution + 102 profile regression +
5 new from this commit — up from 158).
* docs-lint: 0 errors.
* E2E verified: install preview shows ✓/needs-setting per env var,
`profile list` shows Distribution column, `profile show` + `delete`
preview mentions source URL, `info` shows Installed: timestamp.
* fix(profile-dist): clean errors + warn when overwriting plain profiles
Two small polish fixes found during collision sweeps of the PR:
1. ValueError from validate_profile_name now caught cleanly
* A distribution.yaml whose 'name' field can't be used as a profile
identifier (spaces, path traversal, etc.) raises ValueError from
hermes_cli.profiles.validate_profile_name, which was escaping as a
raw Python traceback from 'hermes profile install/update/info'.
* Broadened the except clause in all three handlers to catch
(DistributionError, ValueError) — users now see:
Error: Invalid profile name '../../etc/passwd'. Must match
[a-z0-9][a-z0-9_-]{0,63}
instead of a stack trace.
2. Install preview distinguishes plain profile overwrite from
distribution re-install
* When plan.target_dir exists and IS a distribution (has
distribution.yaml), preview still shows the mild
(profile exists — will overwrite distribution-owned files only)
* When plan.target_dir exists but is a HAND-BUILT plain profile (no
distribution.yaml), preview now shows a loud warning:
⚠ Profile exists but is NOT a distribution. Installing here will
overwrite its SOUL.md, skills/, cron/, and mcp.json.
Your memories, sessions, auth.json, and .env will be preserved,
but any hand-edits to distribution-owned files will be lost.
* Users who type 'hermes profile install foo --force' against a
profile they hand-built now see what they're signing up for. User
data is still safe (memories, sessions, auth, .env are in
USER_OWNED_EXCLUDE), but custom SOUL/skills get stomped.
Tests (+2):
* TestErrorSurfaces.test_bad_profile_name_raises_valueerror_not_traceback
* TestErrorSurfaces.test_path_traversal_name_rejected
Validation:
* 165/165 tests pass (was 163).
* E2E: bad manifest names produce 'Error: Invalid profile name ...'
with no traceback; installing over a plain profile shows the warning;
re-installing over an existing distribution shows the normal
overwrite message.
* Bad HTTPS URLs still produce 'Error: git clone failed: ...' — git
itself generates a clean enough message that no wrapper is needed.
* 'install .' works correctly from any cwd.
* fix(profiles): reject reserved names at validate time
Before: `hermes profile create hermes` / `profile install` / `profile rename`
all silently accepted reserved names like `hermes`, `test`, `tmp`, `root`,
`sudo`. The profile directory was created; only alias creation failed (via
check_alias_collision), leaving a confusingly-named profile on disk — e.g.
`~/.hermes/profiles/hermes/` sitting next to `~/.hermes/` itself.
The reserved set already exists (_RESERVED_NAMES, introduced alongside alias
collision detection). This commit moves the check up one layer to
validate_profile_name so every entry point — create, install, import,
rename, dashboard web API — shares the same gate.
The error message points the user at the cause without being cryptic:
Error: Profile name 'hermes' is reserved — it collides with either the
Hermes installation itself or a common system binary. Pick a different
name.
`default` continues to pass through (it's a special alias for ~/.hermes).
_HERMES_SUBCOMMANDS (`chat`, `model`, `gateway`, etc.) stays at
alias-collision time only — those are fine as bare profile names with
`--no-alias`.
Tests (+5): test_reserved_names_rejected parametrized over the full
_RESERVED_NAMES set, matching the existing pattern in TestValidateProfileName.
No existing test uses a reserved name as a profile identifier (greppped
create_profile("hermes|test|tmp|root|sudo") — zero hits).
Validation:
* 170/170 tests pass in the profile suites.
* E2E: `profile create hermes`, `profile install` with manifest
name=hermes, and `profile install ... --name hermes` all produce the
same clean `Error: Profile name 'hermes' is reserved ...` with rc=1
and no traceback. Normal names (`mybot`) still work.
The prior implementation routed download_to_file through the shared
_request() path, which uses httpx.AsyncClient.request() inside a
context manager that closes before aiter_bytes() iterates. The body
was read into memory first and the chunked write loop replayed it
from buffer. On small test payloads this was invisible; on real
Teams meeting recordings (hundreds of MB) it would force the full
artifact into RAM per download.
Rewrites download_to_file to open its own AsyncClient and use
client.stream(), keeping the context open across the aiter_bytes
iteration so the body is actually streamed chunk-by-chunk to disk.
Retry/token-refresh/Retry-After semantics are preserved by handling
them inline on the stream path. Partial .part files are cleaned up
on transport errors and on exhausted retries.
Adds three tests: large-payload streaming verifies the chunk loop
runs multiple times (discriminator: 512 KiB at chunk_size=65536
yields 8 chunks under streaming, 1 under buffering), transient-5xx
retry recovers after a single retry, and exhausted-retry cleans up
the partial file.
The new _is_gateway_approval_context() widened the gateway classification
to any call with HERMES_SESSION_PLATFORM bound via contextvars. But
cron/scheduler.py binds that same contextvar for delivery routing on
cron jobs that originate from a gateway platform (telegram/discord/etc.),
so those jobs were getting routed through submit_pending with no
listener — blocking indefinitely instead of honoring approvals.cron_mode.
Short-circuit on HERMES_CRON_SESSION before any gateway check. Cron is
always governed by cron_mode config, regardless of where the job was
scheduled from.
Adds regression coverage in TestCronWithGatewayOrigin and records the
contributor email mapping for scripts/release.py.
Reported: Ctrl+C during an active /goal loop felt like it did nothing —
the agent would interrupt the current turn, then immediately queue another
continuation and keep going until the session ended or the 20-turn budget
ran out.
Root cause: cli.py's _maybe_continue_goal_after_turn() ran in the finally:
block around self.chat(...) unconditionally. Whether the turn completed
normally, got interrupted, or returned an empty string, the judge ran on
whatever was in conversation_history and — because the judge is fail-open
— a "continue" verdict pushed another CONTINUATION_PROMPT onto
_pending_input. Ctrl+C was invisible to the hook.
Fix:
- chat() now captures result['interrupted'] onto self._last_turn_interrupted
(resets to False at entry so early-returns don't leak prior state).
- _maybe_continue_goal_after_turn() checks the flag first: on interrupt,
auto-pause via mgr.pause(reason='user-interrupted (Ctrl+C)') and print
a one-liner pointing the user at /goal resume or /goal clear. No judge
call, no continuation enqueued.
- Also added an empty-response guard that mirrors gateway/run.py's
_handle_message logic (empty reply → transient failure → skip judging
so we don't trip the consecutive-parse-failures backstop unnecessarily).
The goal stays in the DB as paused, so /goal resume recovers it after
the user has sorted out whatever made them cancel. /goal clear still
works as before for a full stop.
Tests: tests/cli/test_cli_goal_interrupt.py covers:
- interrupted turn pauses + doesn't queue + judge is NOT called
- paused goal is resumable
- empty / whitespace / missing assistant reply skips judging
- healthy turn still enqueues continuation / marks done
- chat() resets _last_turn_interrupted at entry (anti-leak guard)
All 55 existing goal tests still pass.
Adds one reserved token to the cron `deliver` field:
- `all` — expand to every platform with a configured home channel
Resolves at fire time, not create time, so a job created before Telegram
was wired up picks it up once `TELEGRAM_HOME_CHANNEL` is set. Composes
with existing targets: `origin,all`, `all,telegram:-100:17`.
Inspired by Vellum Assistant's reminder routing-intent system.
## Changes
- cron/scheduler.py: _expand_routing_tokens + integrate into _resolve_delivery_targets
- tools/cronjob_tools.py: schema description updated
- tests/cron/test_scheduler.py: TestRoutingIntents (5 cases)
- website/docs/user-guide/features/cron.md: docs + table rows
## Validation
- tests/cron/test_scheduler.py -k 'Routing or Deliver' → 57 passed
The previous revision of this PR added six GMI-specific branches
(`elif base_url_host_matches(..., 'api.gmi-serving.com')`) across
run_agent.py and agent/auxiliary_client.py, plus a _HERMES_UA_HEADERS
constant in auxiliary_client.py.
ProviderProfile already has a `default_headers: dict[str, str]` field
commented as 'Client-level quirks (set once at client construction)'.
Other plugins (ai-gateway, kimi-coding) already use it. Two of the four
auxiliary_client sites we previously patched already had a generic
`else: profile.default_headers` fallback that picked it up (so did
both run_agent sites).
This revision:
* Sets `default_headers={'User-Agent': 'HermesAgent/<ver>'}` on the
GMI profile in plugins/model-providers/gmi/__init__.py.
* Reverts all six GMI-specific branches in run_agent.py and
auxiliary_client.py.
* Adds the generic profile-fallback `else` block to the two
auxiliary_client sites (`_to_async_client`, `resolve_provider_client`)
that didn't have it yet. This benefits every provider whose profile
declares default_headers, not just GMI — e.g. Vercel AI Gateway's
HTTP-Referer/X-Title now flow through the async client path too.
* Replaces the GMI-specific URL-branch tests with a profile-level
assertion and keeps the run_agent integration test (with
`provider='gmi'` so the fallback picks up the profile).
Net diff vs main: +82/-0 across 5 files, touching only the GMI plugin,
two generic fallback blocks in auxiliary_client.py, AUTHOR_MAP, and
tests. No core files change.
Based on #20907 by @isaachuangGMICLOUD.
Weak judge models (e.g. deepseek-v4-flash) return empty strings or prose
when asked for the strict {done, reason} JSON verdict. The old code
failed-open to continue on every such turn, burning the entire turn
budget with log lines like
judge returned empty response
judge reply was not JSON: "Let me analyze whether the goal..."
and /goal clear could not stop it mid-loop without /stop.
After N=3 consecutive *parse* failures (transport/API errors don't
count — those are transient), the loop auto-pauses and prints:
⏸ Goal paused — the judge model (3 turns) isn't returning the
required JSON verdict. Route the judge to a stricter model in
~/.hermes/config.yaml:
auxiliary:
goal_judge:
provider: openrouter
model: google/gemini-3-flash-preview
Then /goal resume to continue.
The counter resets on any usable reply (both "done"/"continue" and
API errors) and persists across GoalManager reloads so cross-session
resumes carry the correct state.
Also fixes test_goal_verdict_send.py sharing a hardcoded session_id
across tests — the shared id only worked because the previous
_post_turn_goal_continuation was a never-awaited coroutine. Now that
PR #19160 made it properly awaited, the xdist test-leakage bug
surfaced. Each test gets a unique session_id via uuid suffix.
Route goal status notices through the platform adapter send API and register post-delivery callbacks so completed-goal notices appear after the final assistant response. Also cancel queued synthetic goal continuations on /goal pause and /goal clear while preserving normal queued user messages.
channels_list was iterating directory.items() directly, yielding
("updated_at", str) and ("platforms", dict) pairs — neither passed
the isinstance(entries_list, list) check, so the inner loop never ran
and every call returned count=0 even when channel_directory.json was
populated.
The writer (gateway/channel_directory.py) wraps the payload as
{"updated_at": ..., "platforms": {...}}; every other reader in the
codebase unwraps via directory.get("platforms", {}). This aligns
channels_list with that convention.
Also tightens the existing test_channels_with_directory test, which
bypassed the bug by asserting against _load_channel_directory() directly
instead of calling channels_list. It now calls the tool end-to-end and
a new test_channels_with_directory_platform_filter covers the filter
path. Both tests fail against the pre-fix code.
Closes#21474
Co-authored-by: chrisworksai <262485129+chrisworksai@users.noreply.github.com>
* feat(kanban): add `specify` — auxiliary LLM fleshes out triage tasks
The Triage column shipped with a placeholder 'a specifier will flesh
out the spec', but the specifier itself was never built. This wires
it up as a dedicated CLI verb.
`hermes kanban specify <id>` calls the auxiliary LLM (configured under
`auxiliary.triage_specifier`) to expand a rough one-liner into a
concrete spec — tightened title plus a body with Goal / Approach /
Acceptance criteria / Out-of-scope sections — then atomically flips
`status: triage -> todo` and recomputes ready so parent-free tasks
go straight to the dispatcher on the same tick.
Surface:
hermes kanban specify <task_id> # single task
hermes kanban specify --all [--tenant T] # sweep triage column
hermes kanban specify ... --author NAME # audit-comment author
hermes kanban specify ... --json # one JSON line per task
Design choices:
- Parent gating is preserved. specify_triage_task flips to 'todo',
then recompute_ready promotes to 'ready' only when parents are
done — same rule as a normal parent-gated todo.
- No daemon, no background watcher. Every invocation is explicit —
keeps cost predictable and doesn't fight the dispatcher loop.
- Response parse is lenient: strict JSON preferred, markdown-fence
tolerated, raw-body fallback on malformed JSON so the LLM can't
strand a task in triage.
- All failure modes (no aux client, API error, task moved out of
triage mid-call) return SpecifyOutcome(ok=False, reason=...) so
--all continues past individual failures.
Changes:
hermes_cli/kanban_db.py + specify_triage_task()
hermes_cli/kanban_specify.py NEW (~220 LOC — prompt, parse, call)
hermes_cli/kanban.py + specify subcommand + _cmd_specify
hermes_cli/config.py + auxiliary.triage_specifier task slot
website/docs/user-guide/features/kanban.md specify + config notes
website/docs/reference/cli-commands.md CLI reference entry
tests/hermes_cli/test_kanban_specify_db.py NEW (10 tests)
tests/hermes_cli/test_kanban_specify.py NEW (20 tests)
Validation: 30/30 targeted tests pass. E2E: triage task -> specify ->
ends in 'ready' with events [created, specified, promoted] and the
audit comment recorded under the configured author.
* feat(kanban): wire specifier into dashboard and gateway slash
Follow-ups to the initial PR #21435 — closes the two gaps I'd left as
post-merge: dashboard button and first-class gateway surface.
Dashboard (plugins/kanban/dashboard/)
- POST /tasks/:id/specify NEW endpoint. Thin wrapper around
kanban_specify.specify_task(). Returns the CLI outcome shape
({ok, task_id, reason, new_title}); ok=false with a human reason
is a 200, not a 4xx, so the UI can render it inline without
treating 'no aux client configured' as a crash.
- Runs sync in FastAPI's threadpool because the LLM call can take
tens of seconds on reasoning models.
- Pins HERMES_KANBAN_BOARD around the specify call so the module's
argless kb.connect() lands on the right board.
- dist/index.js: doSpecify callback threaded through the drawer →
TaskDetail → StatusActions prop chain. ✨ Specify button appears
ONLY when task.status === 'triage' (elsewhere the backend would
reject anyway — hide the button to keep the action row clean).
Busy state (Specifying…) + inline success/error banner under the
button using the response.reason text.
- dist/style.css: tiny hermes-kanban-msg-ok / -err classes using
existing --color vars so themes reskin cleanly.
Gateway slash (/kanban specify)
- Already works via the existing run_slash → build_parser →
kanban_command pipeline. No code change needed — slash commands
inherit the argparse tree automatically. Added coverage:
test_run_slash_specify_end_to_end (create --triage, specify, verify
promotion + retitle) and test_run_slash_specify_help_is_reachable.
Tests
- tests/plugins/test_kanban_dashboard_plugin.py: 3 new tests for the
REST endpoint — happy path, non-triage rejection as ok=false 200,
missing aux client as ok=false 200.
- tests/hermes_cli/test_kanban_cli.py: 2 new slash-surface tests.
Docs
- website/docs/user-guide/features/kanban.md: dashboard action row
description mentions ✨ Specify + all three surfaces. REST table
gains /tasks/:id/specify. Slash examples include /kanban specify.
Validation: 340/340 targeted tests pass. E2E via TestClient: create a
triage task over REST → POST /specify with mocked aux client → task
moves to 'ready' column on /board with new title and body applied.
Both implement WebSearchProvider via tools/web_providers/ — matching the
existing SearXNG pattern (PR #5c906d702). Search-only; pair with any
extract provider via web.extract_backend.
- tools/web_providers/brave_free.py — Brave Search API (free tier, 2k
queries/mo). Uses BRAVE_SEARCH_API_KEY as X-Subscription-Token.
- tools/web_providers/ddgs.py — DuckDuckGo via the ddgs Python package.
No API key; gated on package importability.
- tools/web_tools.py: both backends added to _get_backend() config list
and auto-detect chain (trails paid providers), _is_backend_available,
web_search_tool dispatch, web_extract_tool + web_crawl_tool search-only
refusals, check_web_api_key, and the __main__ diagnostic. Introduces
_ddgs_package_importable() helper so tests can monkeypatch a single
symbol for the ddgs availability check.
- hermes_cli/tools_config.py: picker entries for both providers; ddgs
gets a post_setup handler that runs `pip install ddgs`.
- hermes_cli/config.py: BRAVE_SEARCH_API_KEY in OPTIONAL_ENV_VARS.
- scripts/release.py: AUTHOR_MAP entry for @Abd0r.
- tests: 14 new tests (brave-free) + 15 new tests (ddgs) covering
provider unit behavior, backend wiring, and search-only refusals.
Salvages the brave-free + ddgs portion of PR #19796. Not included: the
in-line helpers in web_tools.py (replaced with provider modules to match
the shipped architecture), the lynx-based extract path (these backends
should refuse extract with a clear error — users pair with a real
extract provider), and scripts/start-llama-server.sh (unrelated).
Co-authored-by: Abd0r <223003280+Abd0r@users.noreply.github.com>
Extends PR #21400's resource inlining with image-specific handling: ACP
resource_link and embedded blob resources with an image/* mime (or image
file suffix when mime is missing) now emit an OpenAI image_url part
with a base64 data URL, so vision models actually see the image
instead of a [Binary file omitted] note. Non-image resources keep the
existing text-inlining behavior.
Adds 3 tests: local PNG via resource_link, JPEG mime inferred from
suffix when client omits mimeType, and embedded blob PNG.
The May 5 refactor in d5357f816 made _message_thread_id_for_typing()
symmetric with _message_thread_id_for_send() by mapping the General
topic (thread id "1") to None upfront for both. That's correct for
sendMessage — Telegram rejects message_thread_id=1 on sends and the
topic must be omitted — but it's wrong for sendChatAction.
Observed behavior (confirmed via before/after Telegram wire traces):
Before d5357f816: thread_id=1 → message_thread_id=1 → bubble visible in General
After d5357f816: thread_id=1 → message_thread_id=None → no visible typing
Omitting message_thread_id on sendChatAction does NOT fall back to
the General topic's view in a forum-enabled supergroup; the bubble
ends up hidden from the client's General-topic pane entirely. For
any user on a forum-group, the typing indicator stopped appearing.
Fix: drop the symmetric "1 → None" mapping from the typing resolver.
sendMessage still maps 1 → None via _message_thread_id_for_send (that
side was never broken). The asymmetry is real and required by
Telegram's API — document it in the resolver docstring.
Partial revert of d5357f816; restores the behavior from 0cf7d570e
("fix(telegram): restore typing indicator and thread routing for
forum General topic"). Does not re-introduce the retry-without-thread
fallback that 41545f7ec scoped down for DM topics — with the resolver
fixed, the first call already hits the right wire shape.
Test updated from test_send_typing_general_topic_uses_none_thread_id
(which encoded the broken contract) to
test_send_typing_preserves_general_topic_thread_id, asserting the
single correct call with message_thread_id=1. 10 other tests in the
file untouched and passing.
When empty-response terminal scaffolding fires on a tool-result turn,
_drop_trailing_empty_response_scaffolding left the live history ending at
a bare 'tool' message. The next user input then landed as [...tool, user],
a protocol-invalid sequence that OpenRouter/Opus and other providers
silently fail on (returns empty content). That retriggered the empty-retry
recovery every turn, and recovery flags never hit SQLite (no column for
them), so history kept looking broken on every reload.
Two fixes:
1. Scaffolding strip rewinds the orphan assistant(tool_calls)+tool pair
after popping sentinels. Only fires when scaffolding flags were
actually present, so mid-iteration tool loops are untouched.
2. _repair_message_sequence runs right before every API call as a
defensive belt: drops stray tool messages with unknown tool_call_ids,
merges consecutive user messages so no user input is lost. Does NOT
rewind assistant(tool_calls)+tool+user — that pattern is valid when
the user redirected before the model got its continuation turn.
Repro: session 20260507_044111_fa7e65. Opus-4.7/OpenRouter returned
content-less response after a 42KB execute_code output, nudge+retry
chain exhausted (no fallback configured), terminal sentinel appended,
scaffolding stripped leaving bare tool tail, user typed 'wtf happened..'
and landed as tool→user violation. Every subsequent turn collapsed in
<50ms with the same 3-retry empty chain because the API request itself
was malformed.
Verified live via HTTP mock: pre-fix reproduced 5 api_calls/0.15s exit
'empty_response_exhausted'; post-fix 1 api_call/0.10s exit
'text_response(finish_reason=stop)'. Three-turn session flows cleanly
through the scenario. Full run_agent suite: 1242 passed (0 regressions,
2 pre-existing concurrent_interrupt failures unrelated).
cmd_update's auto-restart path could leave the gateway dead after a
transient failure in systemd's own auto-restart window. Reproduced
on Ubuntu 25.10 + systemd 257: after update, gateway drains and exits 75,
systemd's first respawn 60s later fails (status=200/CHDIR with
"No such file or directory" on a WorkingDirectory that demonstrably
exists), the unit ends up in RestartMaxDelaySec=300 backoff, and
cmd_update's fallback 'systemctl restart' never recovers it — leaving
users with a permanently silent gateway until they manually run
'systemctl reset-failed'.
The fix mirrors the recovery pattern 'hermes gateway restart'
(systemd_restart) got in PR #20949: always reset-failed before
restart, on both the initial fallback and the retry. Also rewrites
the final failure message to tell the user to reset-failed +
restart (not just restart, which is the step that already failed
twice).
cron/scheduler.py:run_job() constructed AIAgent(...) without ever calling
discover_mcp_tools(). The CLI and gateway paths do this at startup; cron
jobs inherited none of it and the user's configured mcp_servers were
invisible inside every cron run.
Insert discover_mcp_tools() right before AIAgent(), wrapped in try/except
so a broken MCP server can't kill an otherwise-working cron job. The call
is idempotent: register_mcp_servers() short-circuits on already-connected
servers, so subsequent ticks in the same scheduler process pay ~0ms.
Scoped to the LLM path only; no_agent script jobs skip it entirely.
Closes#4219.
Makes the in-tree QQ inline keyboards actually light up when the agent
blocks on a dangerous-command approval. Matches the cross-adapter
gateway contract already implemented by Discord, Telegram, Slack,
Matrix, and Feishu.
Gateway/run.py's _approval_notify_sync checks type(adapter).send_exec_approval
and falls back to a text prompt when it's missing. Without this wiring,
QQ users stared at plain '/approve' text even though the adapter shipped
button primitives.
### send_exec_approval(chat_id, command, session_key, description, metadata)
Matches the signature the gateway calls with. Builds an ApprovalRequest
(command_preview, description, timeout) and delegates to send_approval_request.
Uses the last inbound msg_id as reply_to so QQ accepts the passive
message. The 'metadata' parameter is accepted for contract parity but
intentionally unused — QQ doesn't have thread_id/DM-targeting overrides.
### send_update_prompt(chat_id, prompt, default, session_key, metadata)
Signature updated to match the cross-adapter contract used by
'hermes update --gateway' watcher. Renders a 'Update Needs Your Input'
prompt with the optional default hint and a Yes/No keyboard. Replaces
the earlier 3-arg helper that wasn't wired anywhere.
### Default interaction dispatcher
_default_interaction_dispatch() auto-registered as the adapter's
interaction callback in __init__. Routes:
- approve:<session_key>:<decision> → tools.approval.resolve_gateway_approval
Button → choice mapping:
allow-once → 'once'
allow-always → 'always'
deny → 'deny'
(QQ's 3-button mobile layout deliberately collapses 'session' + 'always'
into one button; /approve session text fallback remains available.)
- update_prompt:<answer> → atomic write of y/n to ~/.hermes/.update_response
(the detached 'hermes update --gateway' watcher polls this file)
- anything else → logged and dropped
Resolve exceptions are caught and logged — never propagate into the WS
loop. Callers can override via set_interaction_callback() to route
clicks elsewhere or pass None to drop them entirely.
### Net effect
QQ users now get native tap-to-approve UX on dangerous-command prompts
and update-confirmation prompts, without having to type /approve or /deny
as text. The adapter hooks into tools.approval the same way every other
button-capable platform does.
### Tests
14 new tests cover:
- Default callback installed on __init__
- send_exec_approval / send_update_prompt exist as class methods (so the
gateway's type-probe detects them)
- allow-once/always/deny each map to the correct resolve choice
- update_prompt:y / update_prompt:n each write atomically to the response
file (via monkeypatched get_hermes_home)
- Unknown button_data / empty button_data / resolve exceptions are harmless
- send_exec_approval honours last_msg_id reply-to and accepts metadata
- send_update_prompt delegates with correct content + keyboard
Full qqbot suite: 144 passed (72 pre-existing + 72 from this salvage arc).
Also ran tools/test_approval.py alongside — no regressions (276 passed
combined).
Co-authored-by: WideLee <limkuan24@gmail.com>
_scan_cron_prompt ran at cron create/update time on the user-supplied
prompt but skill content loaded inside _build_job_prompt at runtime
was never scanned. Combined with non-interactive auto-approval, a
malicious skill carrying an injection payload could execute with full
tool access every tick.
- cron/scheduler.py: new CronPromptInjectionBlocked exception and
_scan_assembled_cron_prompt helper. _build_job_prompt now routes
both return paths (with skills / without skills) through the helper,
raising on match. run_job catches the exception and returns a clean
(False, blocked_doc, "", error) tuple so the operator sees a BLOCKED
delivery with the scanner result and an audit hint, rather than a
scheduler crash or a silent skip.
- tests/cron/test_cron_prompt_injection_skill.py: 10 regression tests.
Unit coverage on _scan_assembled_cron_prompt (clean/injection/exfil/
invisible-unicode). End-to-end coverage via _build_job_prompt with
planted skills (injection payload, env exfil, zero-width space,
clean control, missing-skill-doesn't-crash). Fixture patches
tools.skills_tool.SKILLS_DIR / HERMES_HOME so planted skills are
visible. Importantly uses the current cron.scheduler module object
(not a top-level import) so tests don't break when other fixtures
reload cron.scheduler — CronPromptInjectionBlocked identity depends
on which module object defined it.
For every connected MCP server we register four "utility" tool schemas
(mcp_<server>_list_resources, read_resource, list_prompts, get_prompt).
The existing gate was `hasattr(server.session, method)` — but
`mcp.ClientSession` defines all four methods on the class regardless of
what the remote server supports, so the gate never filtered anything.
Tools-only servers (e.g. @upstash/context7-mcp which advertises only
`tools`) ended up with 4 dead stubs; every model call to them returned
JSON-RPC -32601 Method not found, which made the model conclude the
server was broken even when the real tools worked.
Capture the `InitializeResult` returned by `await session.initialize()`
on the `MCPServerTask`, then gate each utility schema on the
corresponding `capabilities` sub-object (resources / prompts). A
legacy `hasattr` fallback runs when `initialize_result` is missing
(older test fixtures / not-yet-captured code paths) so pre-existing
behavior is preserved.
Verified against real `mcp.types.InitializeResult` pydantic models:
- Context7 shape (tools only) → 0 utility stubs registered (was 4)
- Resources-only server → 2 stubs (list_resources, read_resource)
- Prompts-only server → 2 stubs (list_prompts, get_prompt)
- Fully capable server → all 4 stubs
Closes#18051.
Co-authored-by: nikolay-bratanov <nikolay-bratanov@users.noreply.github.com>
Follow-up to the previous commit:
- Add _is_loopback_host() helper covering 127.0.0.1, localhost, ::1,
ip6-localhost, ip6-loopback (case-insensitive). Empty/None host is
treated as non-loopback since unset usually means public default bind.
- Fix mixed-indent comment in the safety rail (comment now aligned with
the if-block) and collapse the nested-if into one condition.
- Add TestInsecureNoAuthSafetyRail covering rejection on 0.0.0.0, a LAN
IP, and empty host; allowance on 127.0.0.1/localhost; plus unit-level
parametrized coverage of _is_loopback_host for spellings we can't bind
in the hermetic test env (::1, ip6-localhost, ip6-loopback).
- Pin test_connect_starts_server + test_webhook_deliver_only defaults
to 127.0.0.1 so they keep passing under the new rail.
- Document the behavior in website/docs/user-guide/messaging/webhooks.md.
When a user replies while quoting another message, QQ sets
'message_type = 103' and pushes the referenced message's content +
attachments inside 'msg_elements[0]'. The old adapter ignored
msg_elements entirely, so:
- Bare quote-replies (no user text) surfaced nothing to the LLM.
- Quoted images/files/voice were never downloaded or described.
- Quoted voice messages specifically produced no transcript — the model
had no way to see what the user was referring to when saying 'about
this voice note…'.
This commit adds _process_quoted_context(d) which extracts msg_elements,
unions their attachments, and runs them through the SAME
_process_attachments pipeline as the main message body. Quoted voice
gets an STT transcript (tried via QQ's asr_refer_text first, then the
configured STT provider); quoted images get cached just like main-body
images; quoted files surface with their original filename intact (not
the CDN URL hash).
The quoted content is prepended to the user's text as a '[Quoted message]:'
block so the LLM sees the full referential context on one turn.
Images-only quotes surface a '[Quoted message]: (image)' marker so the
model knows an image was referenced even if no text came with it.
All four inbound handlers (_handle_c2c_message, _handle_group_message,
_handle_guild_message, _handle_dm_message) now call the helper uniformly
— one merge pattern, not four divergent implementations.
Filename preservation is carried by _process_attachments' existing
'[Attachment: {filename or ct}]' line; nothing else needed for that.
12 new tests under TestProcessQuotedContext and TestMergeQuoteInto cover:
- Non-quote messages short-circuit to empty
- message_type=103 with no msg_elements is harmless
- Text-only quotes render with '[Quoted message]:' prefix
- Voice attachments in the quote flow through STT
- File attachments in the quote preserve the original filename
- Image attachments surface cached paths + media types
- Images-only quote still emits a marker
- Multiple msg_elements are concatenated
- Malformed message_type values return empty
- _merge_quote_into prepends with a blank-line separator
Full qqbot suite: 130 passed (72 existing + 19 chunked + 27 keyboards
+ 12 quoted).
Co-authored-by: WideLee <limkuan24@gmail.com>
The QQ Bot v2 API supports inline keyboards on outbound messages. When a
user taps a button, the platform dispatches an INTERACTION_CREATE
gateway event; the bot ACKs it via PUT /interactions/{id} and decodes
the button's data payload to route the click.
This commit adds:
New module gateway/platforms/qqbot/keyboards.py
- Inline-keyboard dataclasses (InlineKeyboard, KeyboardRow, KeyboardButton,
KeyboardButtonAction, KeyboardButtonRenderData, KeyboardButtonPermission)
that serialize to the JSON shape the QQ API expects.
- build_approval_keyboard(session_key) — 3-button layout:
✅ 允许一次 / ⭐ 始终允许 / ❌ 拒绝, all sharing group_id='approval'
so clicking one greys out the rest.
- build_update_prompt_keyboard() — Yes/No keyboard for update confirms.
- parse_approval_button_data() / parse_update_prompt_button_data() —
decode the button_data payload from INTERACTION_CREATE.
approve:<session_key>:<decision> (decision = allow-once|allow-always|deny)
update_prompt:<answer> (answer = y|n)
- build_approval_text(ApprovalRequest) — markdown renderer for the
surrounding message body (exec-approval and plugin-approval variants,
with severity icons 🔴/🔵/🟡).
- parse_interaction_event(raw) → InteractionEvent dataclass — normalizes
the nested raw payload (id / scene / openids / button_data / etc.).
Adapter changes (gateway/platforms/qqbot/adapter.py)
- _dispatch_payload routes INTERACTION_CREATE → _on_interaction.
- _on_interaction parses the event, ACKs via PUT /interactions/{id}, then
invokes a user-registered interaction callback. Exceptions from the
callback are caught and logged (never propagate into the WS loop).
- set_interaction_callback(cb) lets gateway wiring register a routing
handler that inspects button_data and resolves the corresponding
pending approval / update prompt.
- _send_c2c_text / _send_group_text now accept an optional keyboard kwarg
and append it to the outbound body.
- send_with_keyboard(chat_id, content, keyboard, reply_to=None) — public
helper that sends a single short message with a keyboard attached.
Does NOT chunk-split (a keyboard message has one interactive surface).
Guild chats are rejected non-retryably — they don't support keyboards.
- send_approval_request(chat_id, ApprovalRequest, reply_to=None) +
send_update_prompt(chat_id, content, reply_to=None) — convenience
wrappers over send_with_keyboard.
Tests
27 new unit tests under TestApprovalButtonData, TestUpdatePromptButtonData,
TestBuildApprovalKeyboard, TestBuildUpdatePromptKeyboard, TestBuildApprovalText,
TestInteractionEventParsing, and TestAdapterInteractionDispatch. Cover:
- Button-data round-trip (build → parse returns original session/decision)
- Keyboard JSON shape + mutual-exclusion group_id
- Exec vs plugin approval text templates + severity icons
- Interaction event parsing (c2c / group / guild scene codes)
- _on_interaction end-to-end: ACK invoked, callback receives parsed event,
callback exceptions are swallowed, missing id skips ACK, no registered
callback is harmless.
Full qqbot suite: 118 passed (72 existing + 19 chunked + 27 keyboards).
Co-authored-by: WideLee <limkuan24@gmail.com>
The v2 'single POST /v2/{users|groups}/{id}/files' upload path is capped
at ~10 MB inline (base64 'file_data' or 'url'). For larger files the QQ
platform provides a three-step flow:
1. POST /upload_prepare → upload_id + pre-signed COS part URLs
2. PUT each part to its COS URL → POST /upload_part_finish
3. POST /files with {upload_id} → file_info token
This commit adds a new gateway/platforms/qqbot/chunked_upload.py module
that implements the flow, wires it into QQAdapter._send_media for local
files (URL uploads keep the existing inline path), and introduces
structured exceptions so the caller can surface actionable error text:
- UploadDailyLimitExceededError (biz_code 40093002, non-retryable)
- UploadFileTooLargeError (file exceeds the platform limit)
Both carry file_name / file_size_human / limit_human so the model can
compose user-friendly replies instead of seeing opaque HTTP codes.
The part_finish 40093001 retryable-error loop respects the server-
provided retry_timeout (capped at 10 minutes locally) with a 1 s
polling interval. COS PUTs retry transient failures up to 2 times
with exponential backoff. complete_upload retries up to 2 times.
Covers files up to the platform's ~100 MB per-file limit; before this
the adapter silently rejected anything over ~10 MB.
19 new unit tests under TestChunkedUpload* cover the happy path,
prepare-response parsing, helper functions, part retries, COS PUT
retries, group vs c2c routing, and the structured-error mapping.
Co-authored-by: WideLee <limkuan24@gmail.com>
Adds a per-task override for the consecutive-failure circuit breaker,
so individual tasks can opt out of the global ``kanban.failure_limit``
without dragging everyone else with them.
Resolution order (now three tiers):
1. per-task ``max_retries`` (new, this commit)
2. caller-supplied ``failure_limit`` — the gateway threads
``kanban.failure_limit`` from config here
3. ``DEFAULT_FAILURE_LIMIT`` (2)
Changes:
- ``tasks.max_retries INTEGER`` column + migration for existing DBs
(NULL = no override, matches pre-column behavior).
- ``Task.max_retries`` field + ``from_row`` plumbing.
- ``create_task(..., max_retries=N)`` kwarg.
- ``_record_task_failure`` reads the per-task value first and records
``limit_source`` + ``effective_limit`` on the ``gave_up`` event so
operators can see which tier won.
- CLI: ``hermes kanban create --max-retries N`` (rejects ``< 1``).
- CLI: ``hermes kanban show`` surfaces the effective threshold +
source (``(task)``, ``(config kanban.failure_limit)``, ``(default)``).
- CLI: ``_task_to_dict`` includes ``max_retries`` in ``--json`` output.
Key design choice vs. the earlier #20972 attempt:
- No new config key. The existing ``kanban.failure_limit`` (landed in
#21183) is the dispatcher-tier source — no silent break for users
who already tuned it.
- No ``!=`` sentinel for "is config set" (which would misfire when
config equals the default). The tier-winner is determined purely
by "is per-task override set" — the dispatcher always wins when
per-task is NULL, regardless of whether the caller passed the
default or a configured value.
E2E verified across four scenarios: default-only (trips at 2),
config-only (trips at caller's value), per-task-only beats default
(trips at task value), per-task beats larger config (trips at task
value). ``gave_up`` event metadata correctly records ``limit_source``
and ``effective_limit`` in all cases.
Tests:
- ``test_per_task_max_retries_overrides_dispatcher_limit`` — task=1
beats caller=10.
- ``test_per_task_max_retries_allows_more_than_default`` — task=5
does not trip at caller=default of 2.
- ``test_max_retries_none_falls_through_to_dispatcher_limit`` — None
honors caller's config value (4), records ``limit_source=dispatcher``.
Full kanban trio (db + core + cli + tools + dashboard-plugin): 342
passed, no regressions.
Supersedes: #20972 (@jelrod27) — credit in PR close comment.
Ref: #20263 (tangentially — the reporter asked about adapter API
drift, not retry caps, but the CLI discussion there is what
surfaced the original ask).
PairingStore.approve_code() didn't consult _is_locked_out(), so after
MAX_FAILED_ATTEMPTS bad approvals the lockout flag was set but a valid
code still got accepted — any pending code (legitimately issued or
attacker-obtained) could be approved during the 1-hour lockout window,
nullifying the brute-force protection.
- gateway/pairing.py: lockout check runs in approve_code() right after
_cleanup_expired, before the pending lookup. Returns None on lockout.
- tests/gateway/test_pairing.py: test_lockout_blocks_code_approval pins
the regression — reporter's exact reproducer (generate valid code,
exhaust attempts with WRONGCODE, try to approve valid code) must
return None and leave is_approved == False. Also pins recovery: once
lockout expires, the still-pending code approves normally.
- hermes_cli/pairing.py: _cmd_approve distinguishes the two None cases.
On lockout, prints 'Platform locked out... clears in N minutes. To
reset sooner, delete the _lockout:<platform> entry from
_rate_limits.json' instead of the misleading 'Code not found or
expired' message. 29/29 pairing tests pass; E2E-verified with
reporter's exact Python reproducer.
Adds Google Chat as a new gateway platform, shipped under
plugins/platforms/google_chat/ following the canonical bundled-plugin
pattern (Teams, IRC). Rewired from the original PR #18425 to use the
new env_enablement_fn + cron_deliver_env_var plugin interfaces landed
in the preceding commit, so the adapter touches ZERO core files.
What it does:
- Inbound DM + group messages via Cloud Pub/Sub pull subscription (no
public URL needed), with attachments (PDFs, images, audio, video)
downloaded through an SSRF-guarded Google-host allowlist.
- Outbound text replies with the 'Hermes is thinking…' patch-in-place
pattern — no tombstones.
- Native file attachment delivery via per-user OAuth. Google Chat's
media.upload endpoint rejects service-account auth, so each user
runs /setup-files once in their own DM to grant
chat.messages.create for themselves; the adapter then uploads as
them. Tokens stored per email at
~/.hermes/google_chat_user_tokens/<email>.json.
- Thread isolation: side-threads get isolated sessions, top-level DM
messages share one continuous session. Persistent thread-count
store survives gateway restart.
- Supervisor reconnect with exponential backoff.
- Multi-user out of the box.
How it plugs in (no core edits):
- env_enablement_fn seeds PlatformConfig.extra with project_id,
subscription_name, service_account_json, and the home_channel dict
(which the core hook turns into a HomeChannel dataclass). Reads
GOOGLE_CHAT_PROJECT_ID (falls back to GOOGLE_CLOUD_PROJECT),
GOOGLE_CHAT_SUBSCRIPTION_NAME (falls back to GOOGLE_CHAT_SUBSCRIPTION),
GOOGLE_CHAT_SERVICE_ACCOUNT_JSON (falls back to
GOOGLE_APPLICATION_CREDENTIALS), GOOGLE_CHAT_HOME_CHANNEL.
- cron_deliver_env_var='GOOGLE_CHAT_HOME_CHANNEL' gets cron delivery
for free — cron/scheduler.py consults the platform registry for any
name not in its hardcoded built-in sets.
- plugin.yaml's rich requires_env / optional_env blocks auto-populate
OPTIONAL_ENV_VARS via the new hermes_cli/config.py injector, so
'hermes config' UI surfaces them with description / url / prompt /
password metadata.
- Module-level Platform('google_chat') call in adapter.py triggers the
Platform._missing_() registration so Platform.GOOGLE_CHAT attribute
access works without an enum entry.
Distribution: ships inside the existing hermes-agent package. Users
opt in via 'pip install hermes-agent[google_chat]' and follow the
8-step GCP walkthrough at
website/docs/user-guide/messaging/google_chat.md.
Test coverage: 153 tests in tests/gateway/test_google_chat.py, all
passing. Spans platform registration, env config loading, Pub/Sub
envelope routing, outbound send + chunking + typing patch-in-place,
attachment send paths, SSRF guard, thread/session model,
supervisor reconnect, authorization, per-user OAuth, and the new
plugin-registry cron delivery wiring.
Credit: adapter + OAuth + tests + docs authored by @donramon77
(PR #18425). Rewire onto the new plugin hooks + salvage commit by
Teknium.
Co-Authored-By: Ramón Fernández <112875006+donramon77@users.noreply.github.com>
MCP tool results can include ImageContent blocks (screenshots from
Playwright/Blockbench/Puppeteer etc). The tool result handler only
extracted block.text, so image blocks were silently dropped and the
agent saw an empty or text-only response — losing the actual payload.
Add _cache_mcp_image_block() that base64-decodes the block, validates
the bytes via gateway.platforms.base.cache_image_from_bytes (which
sniffs for PNG/JPEG/WebP signatures and rejects non-images), writes to
the shared `~/.hermes/cache/images/` dir, and returns a MEDIA:<path>
tag. The handler appends that tag to the result parts so downstream
gateway adapters render the image inline.
Logs and drops on malformed base64 / non-image payload rather than
raising — a single bad block shouldn't kill the tool call.
Distilled from #17915 (c3115644151) and #10848 (gnanirahulnutakki), both
too stale to cherry-pick (branches diverged enough to revert dozens of
unrelated fixes). Went with #10848's approach of plumbing through
Hermes' existing MEDIA tag / cache_image_from_bytes infrastructure
rather than #17915's raw tempfile path, because it integrates with the
remote-backend mount system and messaging adapters that already handle
MEDIA tags natively.
Co-authored-by: c3115644151 <c3115644151@users.noreply.github.com>
Co-authored-by: gnanirahulnutakki <gnanirahulnutakki@users.noreply.github.com>
* fix(mcp): re-raise CancelledError explicitly in MCPServerTask.run
On Python 3.11+, `asyncio.CancelledError` inherits from `BaseException`
(not `Exception`), so the broad `except Exception as exc:` in
`MCPServerTask.run`'s transport loop did NOT catch it. Task cancellation
from gateway restart / explicit `task.cancel()` silently escaped past
the reconnect logic — the MCP server task died without going through
the shutdown/reconnect code paths that check `_shutdown_event`.
Add an explicit `except asyncio.CancelledError: raise` before the broad
catch so cancellation propagation is self-documenting rather than an
accident of exception hierarchy, and future sibling-site work (e.g.
distinguishing shutdown-cancel from transport-cancel) has an obvious
hook. Behavior on pre-3.8 Pythons where CancelledError WAS an Exception
subclass is also corrected: the old path would have caught it and
treated it as a connection failure worth retrying.
Closes#9930.
* fix(mcp): forward OAuth auth and bump sse_read_timeout on SSE transport
Two surgical correctness bugs in the SSE branch of MCPServerTask._run_http,
distilled from @amiller's PR #5981 that couldn't be cherry-picked wholesale
(branch too stale).
1. sse_read_timeout was set to the tool timeout (default 60s). That's the
wrong dimension — it governs how long sse_client will wait between
events on the SSE stream, not per-call latency. SSE servers routinely
hold the stream idle for minutes between events; a 60s read timeout
drops the connection after the first slow stretch (Router Teamwork,
Supermemory on Cloudflare Workers idle-disconnect at ~60s). Bump to
300s to match the Streamable HTTP path's httpx read timeout.
2. OAuth auth was built via get_manager().get_or_build_provider() but
never forwarded to sse_client. SSE MCP servers behind OAuth 2.1 PKCE
would silently fail with 401s on every request.
Keepalive (the other half of #5981) intentionally left for a follow-up —
it's a real improvement but a bigger change, and these two are obvious
corrections to ship now. Credits to @amiller.
Co-authored-by: Andrew Miller <socrates1024@gmail.com>
---------
Co-authored-by: Andrew Miller <socrates1024@gmail.com>
On Python 3.11+, `asyncio.CancelledError` inherits from `BaseException`
(not `Exception`), so the broad `except Exception as exc:` in
`MCPServerTask.run`'s transport loop did NOT catch it. Task cancellation
from gateway restart / explicit `task.cancel()` silently escaped past
the reconnect logic — the MCP server task died without going through
the shutdown/reconnect code paths that check `_shutdown_event`.
Add an explicit `except asyncio.CancelledError: raise` before the broad
catch so cancellation propagation is self-documenting rather than an
accident of exception hierarchy, and future sibling-site work (e.g.
distinguishing shutdown-cancel from transport-cancel) has an obvious
hook. Behavior on pre-3.8 Pythons where CancelledError WAS an Exception
subclass is also corrected: the old path would have caught it and
treated it as a connection failure worth retrying.
Closes#9930.
PR #21238 introduced top-level `allOf: [{if/then/required}]` blocks in the
built-in memory tool's parameters schema as conditional-required hints.
Two problems:
1. OpenAI's Codex backend (chatgpt.com/backend-api/codex, gpt-5.x) rejects
top-level `allOf`/`anyOf`/`oneOf`/`enum`/`not` outright with a
non-retryable 400 — affected every user on openai-codex/gpt-5.x.
2. The `if/then` hints were silently ignored by every other provider
(Chat Completions doesn't honour them on function schemas), so they
never actually enforced anything anywhere.
The runtime handler in `memory_tool()` already validates the per-action
required fields and returns actionable error messages, so removing the
block changes nothing behaviourally.
Paired with the defense-in-depth sanitizer in the previous commit, this
closes the bug both at the source (schema no longer emits the forbidden
form) and at the wire boundary (sanitizer strips it if anything else
re-introduces it).
- Rewrites `tests/tools/test_memory_tool_schema.py` to guard against
regressing the forbidden-combinator shape instead of asserting it.
- Adds AUTHOR_MAP entry for @hrkzogw (author of the sanitizer fix).
Mirrors the Slack `allowed_channels` feature (PR #7401) and Discord's
`allowed_channels` (PR #7044) across the remaining group-capable platforms.
All five platforms (Slack + Discord + the four added here) now follow the
same pattern: primary config via config.yaml, env-var fallback as an escape
hatch — matching the project policy that .env is for secrets only and
behavioral settings belong in config.yaml.
Also fixes a duplicate `slack` key in DEFAULT_CONFIG introduced by PR
#7401 (the later entry silently overwrote `allowed_channels`, `require_mention`,
and `free_response_channels` at dict-literal evaluation time).
Platforms added:
- Telegram: `telegram.allowed_chats` (env alias: `TELEGRAM_ALLOWED_CHATS`)
- Mattermost: `mattermost.allowed_channels` (env alias: `MATTERMOST_ALLOWED_CHANNELS`)
- Matrix: `matrix.allowed_rooms` (env alias: `MATRIX_ALLOWED_ROOMS`)
- DingTalk: `dingtalk.allowed_chats` (env alias: `DINGTALK_ALLOWED_CHATS`)
Mattermost and Matrix previously had NO config.yaml bridging for any of
their gating settings; this PR adds `load_gateway_config` bridges for them
(Mattermost gets require_mention + free_response_channels + allowed_channels;
Matrix gets allowed_rooms on top of its existing bridges for require_mention
and free_response_rooms).
Semantics identical everywhere:
- Empty = no restriction (fully backward compatible).
- Non-empty = hard whitelist: non-listed chats are silently ignored,
even when the bot is @mentioned.
- DMs bypass the check entirely.
DEFAULT_CONFIG merges the duplicate `slack` block and adds new `mattermost`
and `matrix` blocks so all gating settings surface in defaults.
Not included: Feishu (has its own per-chat `chat_rules` system that covers
this use case differently), WhatsApp (already has `group_allow_from` via
`group_policy: allowlist`), pure-DM platforms (Signal, SMS, BlueBubbles,
Yuanbao — no group concept).
When the parent agent uses a composite toolset like hermes-cli, calling
delegate_task with individual toolsets (e.g. web, terminal) resulted in
zero tools because the name-based intersection failed: 'web' != 'hermes-cli'.
Add _expand_parent_toolsets() which collects all tool names from parent
toolsets, then recognises any individual toolset whose tools are a subset
of the parent's available tools. This allows delegate_task(toolsets=['web'])
to work correctly when the parent has hermes-cli enabled.
Fixes#19447
Add tencent/hy3-preview (without :free suffix) as a paid model route
alongside the existing free variant. This allows seamless transition
when the model moves from free to paid on OpenRouter — both routes
coexist so neither side's timing causes breakage.
Changes:
- models.py: add ("tencent/hy3-preview", "") to OPENROUTER_MODELS
- model-catalog.json: add paid variant entry
- tests: add assertions for paid route presence
The :free entry can be removed in a follow-up PR once OpenRouter
confirms the free route is deprecated.
Co-authored-by: simonweng <simonweng@tencent.com>
Some exception classes (e.g. anyio.ClosedResourceError) are raised without
a message argument, so str(exc) returns an empty string. The existing error
format f'{type(exc).__name__}: {exc}' would produce messages like
'MCP call failed: ClosedResourceError: ' with nothing after the colon.
Add _exc_str() helper that falls back to repr(exc) when str(exc) is empty,
and apply it to all 6 MCP error formatting sites (5 tool/prompt/resource
handlers + 1 sampling handler).
Fixes#19417
Treat closed-resource, closed-transport, broken-pipe, and EOF MCP failures as stale session equivalents so the existing reconnect/retry-once path can recover. Add regression coverage for the stale-pipe marker variants.\n\nChecks:\n- python -m py_compile tools/mcp_tool.py tests/tools/test_mcp_tool_session_expired.py\n- python -m pytest tests/tools/test_mcp_tool_session_expired.py -q -o addopts=\n- selected secret scan over touched files
Track elapsed wall time in _run_on_mcp_loop, cancel the in-flight future when a timeout expires, and raise a descriptive TimeoutError that includes the elapsed and configured timeout. Add regression coverage for the new timeout diagnostics.
## Summary
- Forwards chat-completions `timeout` into the Codex Responses stream call.
- Adds total elapsed-time enforcement while the Responses stream is still yielding events.
- Closes the underlying client on timeout to unblock stalled streams, then raises `TimeoutError`.
- Adds focused tests for timeout forwarding and total timeout enforcement.
## Why
The Codex auxiliary adapter can be used by non-interactive auxiliary work such as context compression. If the stream keeps yielding progress-like events but never completes, SDK socket/read timeouts do not necessarily protect the full operation. This makes the CLI look stuck until the user force-interrupts the whole session.
This is a refreshed upstream-ready version of the earlier fork fix around `d3f08e9a0` / PR #3.
## Verification
- `python -m py_compile agent/auxiliary_client.py tests/agent/test_auxiliary_client.py`
- `python -m pytest -o addopts='' tests/agent/test_auxiliary_client.py::TestCodexAuxiliaryAdapterTimeout -q`
- `git diff --check`
Discord (and similar platforms) can serve a PNG image cached as
discord_xxx.webp because the CDN reports content_type=image/webp for
proxied stickers, custom emoji, and certain bot-uploaded images even
when the actual bytes are PNG. Hermes' agent.image_routing._guess_mime
trusted the file suffix and declared media_type=image/webp to
Anthropic, which strict-validates and returns:
HTTP 400 messages.N.content.M.image.source.base64:
The image was specified using the image/webp media type,
but the image appears to be a image/png image
The Discord image attachment never reaches the model; the whole turn
fails with no salvage path.
Fix: sniff magic bytes in _file_to_data_url before declaring MIME.
Suffix-based detection is kept as a fallback when bytes aren't
available. New helper _sniff_mime_from_bytes covers PNG, JPEG, GIF,
WEBP, BMP, and HEIC/HEIF.
Tests:
- Two existing tests asserted the old broken behaviour (PNG bytes in
a .jpg/.webp file should report jpeg/webp); rewritten with real
jpeg/webp magic bytes so they still cover suffix-aligned cases.
- New regression test test_mime_sniff_overrides_misleading_extension
reproduces the exact Discord scenario (PNG bytes, .webp suffix) and
asserts the data URL comes back as image/png.
All 28 tests in tests/agent/test_image_routing.py pass.
When the provider rejects a request (e.g. invalid model slug like
'--provider nous --model kimi-k2.6' where the valid slug is
'moonshotai/kimi-k2.6'), run_conversation() returns
{failed: True, error: <detail>, final_response: None}. The TUI gateway
and one-shot CLI mode both dropped the error on the floor and emitted
an empty turn, so the user saw a blank response with no indication
that anything went wrong.
Mirror the interactive CLI's existing pattern (cli.py:9832): when
final_response is empty AND (failed|partial) is set AND error is
populated, surface 'Error: <detail>' as the visible text. Leaves
the None-with-no-error path and the '(empty)' sentinel path
untouched — an empty successful turn still renders empty, and
existing sentinel handlers keep owning their lane.
Reported by @counterposition in PR #20873; taking a minimal fix
rather than the broader structured-failure refactor proposed there.
Per repo policy, ~/.hermes/.env is for secrets only. Guild IDs are
behavioral configuration, not secrets. Replacing the
DISCORD_DM_ROLE_AUTH_GUILD env var from the original fix with
discord.dm_role_auth_guild in config.yaml.
- New module-level _read_dm_role_auth_guild() helper reads
hermes_cli.config.read_raw_config()['discord']['dm_role_auth_guild'].
Fails closed on any parse error (safe default = DM role-auth off).
- DEFAULT_CONFIG['discord'] gains dm_role_auth_guild: '' with a comment
documenting the opt-in.
- Tests patch hermes_cli.config.read_raw_config directly (via the
_set_dm_role_auth_guild helper) instead of setenv/delenv. 12 tests
in test_discord_roles_dm_scope pass; no env var involvement.
- Docstring + module docstring + comments updated to reference
discord.dm_role_auth_guild.
- E2E verified with real imports across 6 scenarios: unset, int,
string, garbage, zero, and (crucially) env-var-only-no-config all
return None except the valid int/string cases. Env var has zero
effect — policy compliance confirmed.
Sibling-site fix: _evaluate_slash_authorization was the fourth
_is_allowed_user caller and didn't pass guild/is_dm through, so slash
interactions would take the DM branch regardless of whether they came
from a guild channel. Now reads interaction.guild + in_dm and forwards.
Also updates test_discord_slash_auth fixture (_make_interaction) so
the SimpleNamespace guild mock has a get_member(uid)->None method —
required by the new guild-scoped fallback path in _is_allowed_user.
Tests exercising positive role paths still work via user.roles.
Three new regression tests in test_discord_roles_dm_scope:
- Slash DM + role in mutual public guild → rejected
- Slash in guild B + role only in guild A → rejected
- Slash in guild B + role in guild B → allowed (positive control)
368 Discord tests pass. test_discord_free_channel_skips_auto_thread
also fails on clean main (pre-existing, unrelated to this fix).
The initial DISCORD_ALLOWED_ROLES implementation (#11608, merged from #9873)
scans every mutual guild when resolving a user's roles. This allows a
cross-guild DM bypass:
1. Bot is in both public server A and private server B.
2. User holds the allowed role in server A only.
3. User DMs the bot. The role check finds the role in A and authorizes the
DM, granting access as if the user were trusted in server B.
Fix:
- DMs (no guild context) disable role-based auth by default. Opt-in via
DISCORD_DM_ROLE_AUTH_GUILD=<guild_id> restricts role lookup to one
explicitly-trusted guild.
- Guild messages check roles only in the originating guild
(message.guild), never in other mutual guilds.
- Reject cached author.roles when the Member came from a different guild
than the current message.
Backwards compatibility:
- DISCORD_ALLOWED_USERS behavior is unchanged (still works in both DMs
and guild messages).
- Deployments that rely on roles in guild channels continue to work;
role checks are now strictly scoped to that guild.
- Deployments that intentionally want role-based DM auth can opt into a
single trusted guild via DISCORD_DM_ROLE_AUTH_GUILD.
Tests: 9 new regression guards in
tests/gateway/test_discord_roles_dm_scope.py covering the bypass path,
the opt-in path, cross-guild guild-message bypass, and backwards-compat
user-ID paths. 47/47 discord-auth tests pass.
Refs: #11608 (initial implementation), #7871 (feature request),
#9873 (PR author credit @0xyg3n)
Authenticated remote OpenViking servers derive tenancy from the Bearer
key, but the client was always sending X-OpenViking-Account and
X-OpenViking-User — defaulted to the literal string "default" — which
overrode the key-derived tenant and broke auth.
- _headers(): skip X-OpenViking-Account/-User when blank or "default"
(treats the legacy default value as unset, so existing installs don't
need to touch their .env)
- _headers(): send Authorization: Bearer <key> alongside X-API-Key for
standard HTTP auth compatibility
- health(): include auth headers so /health works against servers that
require authentication
Tests cover bearer emission, legacy "default" suppression, empty
suppression, real tenant passthrough, and authenticated health checks.
Fixes the same user report as #20695 (from @ZaynJarvis); that PR could
not be merged because its branch was stale against main and would have
reverted recent OpenViking work (#15696, local resource uploads, summary
URI normalization, fs-stat pre-check).
Cloud metadata endpoints (169.254.169.254 etc.) are now always blocked
by browser_navigate regardless of hybrid routing, allow_private_urls,
or backend.
Bug: commit 42c076d3 (#16136) added hybrid routing that flips
auto_local_this_nav=True for private URLs and short-circuits
_is_safe_url(). IMDS endpoints are technically private (169.254/16
link-local), so the sidecar happily routed them to a local Chromium,
and the agent could read IAM credentials via browser_snapshot. On
EC2/GCP/Azure this is a full SSRF-to-credential-theft.
Fix: new is_always_blocked_url() in url_safety.py — a narrow floor
that checks _BLOCKED_HOSTNAMES, _ALWAYS_BLOCKED_IPS,
_ALWAYS_BLOCKED_NETWORKS only. Applied as an independent gate in
browser_navigate's pre-nav and post-redirect checks, BEFORE
auto_local_this_nav gets a chance to short-circuit. Ordinary private
URLs (localhost, 192.168.x, 10.x, .local, CGNAT) still route to the
local sidecar as the #16136 feature intends.
Secondary fix (reporter's finding): _url_is_private() now explicitly
checks 172.16.0.0/12. ipaddress.is_private only covers that range on
Python ≥3.11 (bpo-40791), so on 3.10 runtimes those URLs were routed
to cloud instead of the local sidecar. No security impact — just a
correctness fix for the hybrid-routing feature.
Closes#16234.
The MCP SDK discovers OAuth server metadata (token_endpoint, etc.) on
demand and keeps it in memory only. Without disk persistence, a restart
with valid cached refresh tokens forces the SDK to fall back to the
guessed '{server_url}/token' path — which returns 404 on most real
providers (Notion, Atlassian, GitHub remote MCP, etc.) and triggers a
full browser re-authorization even though the refresh token is fine.
Add a .meta.json file next to the existing tokens/client_info files:
HERMES_HOME/mcp-tokens/<server>.json -- tokens (existing)
HERMES_HOME/mcp-tokens/<server>.client.json -- client info (existing)
HERMES_HOME/mcp-tokens/<server>.meta.json -- oauth metadata (new)
Changes:
- HermesTokenStorage.save_oauth_metadata / load_oauth_metadata / _meta_path
— disk layer for the discovered OAuthMetadata.
- HermesTokenStorage.remove() now also clears .meta.json so
'hermes mcp remove <name>' and the manager's remove() path clean up fully.
- HermesMCPOAuthProvider._initialize cold-restores from disk before the
existing pre-flight discovery runs. If disk has metadata we skip the
discovery HTTP round-trips entirely.
- HermesMCPOAuthProvider._prefetch_oauth_metadata now persists ASM as
soon as it's discovered, so even the first pre-flight run seeds disk.
- HermesMCPOAuthProvider._persist_oauth_metadata_if_changed() is called
at the end of async_auth_flow so metadata discovered via the SDK's
lazy 401-branch (not pre-flight) is also saved for next time.
Tests cover the storage roundtrip (save/load/missing/corrupt/remove) and
the manager provider path (cold-load restore, skip-when-in-memory,
persist-on-discover, noop-when-unchanged, end-to-end async_auth_flow).
Co-authored-by: nocturnum91 <50326054+nocturnum91@users.noreply.github.com>
Drives stream_events directly and cancels the task while it is sleeping
in the poll loop, asserting the coroutine returns cleanly instead of
letting CancelledError bubble. Regression coverage for the Uvicorn
application traceback on dashboard Ctrl-C fixed by the preceding commit.
Address review feedback to use the clamp emoji (��️) instead of
the plain text 'cmp' prefix for the compression count indicator.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Display the number of context compressions in the CLI status bar when
compressions > 0, helping users understand conversation compression
pressure during long sessions.
- Wide layout (>=76 cols): shows 'cmp N' between context percent and duration
- Medium layout (52-75 cols): shows 'cmp N' between percent and duration
- Narrow layout (<52 cols): omitted to save space
- Color-coded: dim for 1-4, warn for 5-9, bad for 10+
- Hidden when zero to keep the bar clean for new sessions
Closes#18564
When multiple custom_providers share the same base_url but have different API keys,
get_custom_provider_pool_key() always returned the first match, causing wrong-key
unauthorized errors. Add provider_name parameter to prefer exact name matches
over base_url-only matching, with fallback for backward compatibility.
Fixes#19083
When a kanban worker subprocess exits rc=0 but its task is still in
status='running', the agent almost certainly answered the task
conversationally without calling kanban_complete or kanban_block. The
dispatcher used to classify this as a generic crash and respawn, which
loops forever on small local models (gemma4-e2b q4 etc.) that keep
returning clean but unproductive output.
Dispatcher changes:
- The waitpid reap loop at the top of dispatch_once now records each
reaped child's raw exit status in a bounded module registry
(_recent_worker_exits, TTL 600s, size cap 4096).
- _classify_worker_exit distinguishes clean_exit / nonzero_exit /
signaled / unknown using os.WIFEXITED / WIFSIGNALED.
- detect_crashed_workers consults the classification when a worker
is found dead. clean_exit → protocol_violation event + immediate
circuit-breaker trip (failure_limit=1). Everything else keeps the
existing crashed-event + counter behavior.
- DispatchResult.auto_blocked now includes protocol-violation trips.
Gateway fix (Bug A in #20894):
- gateway.run._notify_active_sessions_of_shutdown snapshots
self.adapters with list(...) before iterating. adapter.send() can
hit a fatal-error path that pops the adapter from the dict, which
was raising 'RuntimeError: dictionary changed size during iteration'
during shutdown.
Regression tests:
- test_detect_crashed_workers_protocol_violation_auto_blocks verifies
rc=0 + still-running → status=blocked on first occurrence with
protocol_violation + gave_up events and NO crashed event.
- test_detect_crashed_workers_nonzero_exit_uses_default_limit verifies
non-zero exits keep the existing 2-strike behavior.
Closes#20894.
custom_providers entries (section 4 of list_authenticated_providers) only
read the static models: dict from config.yaml, ignoring the live /v1/models
endpoint. This means gateways like Bifrost that expose hundreds of models
only show the handful explicitly listed in config.
Add live discovery via fetch_api_models() for custom_providers entries
that have api_key + base_url, matching the existing behavior for user
providers: entries (section 3). When the endpoint is reachable and
returns models, the live list replaces the static subset.
Fixes: /model picker showing only 9 models from a Bifrost gateway that
actually exposes 581.
Skills that produce large/lossless images (e.g. info-graph, where a
rendered JPG is 1-2 MB) currently lose quality in Telegram delivery
because `_IMAGE_EXTS` membership routes the file through
`send_multiple_images` → `sendMediaGroup`, which Telegram's server
re-encodes to JPEG @ 1280px max edge. The original bytes only survive
when the file goes through `send_document`, which the dispatch tables
in three places (`_process_message_background`, `_deliver_media_from_response`,
and the `send_message` tool's telegram path) only reach for files
whose extension is NOT in `_IMAGE_EXTS`.
This commit adds an `[[as_document]]` directive that mirrors the
existing `[[audio_as_voice]]` shape: a skill emits the directive once
in its response, and every image-extension MEDIA: file in that response
is delivered via `send_document` instead of `send_multiple_images` /
`sendPhoto`. The directive is detected at the dispatch sites (which see
the raw response) and the directive string is stripped from the
user-visible cleaned text in `extract_media` so it never leaks.
Granularity is intentionally all-or-nothing per response, matching
[[audio_as_voice]]'s scope. Skills that need fine control can split into
two responses.
Verified the targeted use case: info-graph emits
信息图已生成（...）
[[as_document]]
MEDIA:/tmp/info-graph-x/infographic.jpg
→ Telegram receives `infographic.jpg` via sendDocument, original 1MB
JPEG bytes preserved, no recompression. Forwarding and download
filenames stay clean (`infographic.jpg`).
Tests: +3 cases in TestExtractMedia covering directive strip, isolation
from voice flag, and coexistence with [[audio_as_voice]]. All
113 pre-existing media/extract/send tests pass.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The --command flag of `hermes mcp add` shared its argparse dest with the
top-level subparser (`dest="command"` in `hermes_cli/_parser.py`). When
the flag was omitted, argparse still wrote `args.command = None`,
clobbering the top-level value of `"mcp"`. The dispatcher then saw
`args.command is None` and fell through to interactive chat, so
`hermes mcp add ...` silently launched chat instead of registering the
server. `cmd_mcp_add` was never reached.
Use `dest="mcp_command"` on the flag and read it from `cmd_mcp_add`.
The user-facing CLI flag `--command` is unchanged; only the in-memory
namespace attribute moves. Also updates the `_make_args` helper in
`tests/hermes_cli/test_mcp_config.py` to populate the new dest, and
adds `tests/hermes_cli/test_mcp_add_command_dest.py` with a parser-
level regression test.
Closes#19785.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Follow-up on top of Zyproth's session-source cache: swap the unbounded
dict for an OrderedDict with a 512-entry LRU cap so long-running
gateways can't accumulate stale entries for dead sessions forever.
- self._session_sources is now an OrderedDict
- _cache_session_source() move_to_end + popitem(last=False) above cap
- _get_cached_session_source() move_to_end on hit (LRU read bump)
- restart_test_helpers.py wires OrderedDict + _session_sources_max
`_save_auth_store`, `_save_qwen_cli_tokens`, and `_write_shared_nous_state`
all created the temp file via `Path.open('w')` / `Path.write_text` and only
tightened permissions to 0o600 afterward. Between create and chmod the file
existed at the process umask (commonly 0o644 = world-readable on multi-user
hosts), briefly exposing OAuth access/refresh tokens for Nous, Codex,
Copilot, Claude, Qwen, Gemini, and every other native OAuth provider that
flows through auth.json.
Switch all three to `os.open(O_WRONLY|O_CREAT|O_EXCL, 0o600)` + `os.fdopen`
+ `fsync` so the file is atomic at 0o600 on creation. Tighten each parent
directory (`~/.hermes/`, Qwen auth dir, Nous shared auth dir) to 0o700 so
siblings can't traverse to the creds. `_save_auth_store` also gains a
per-process random temp suffix to match `agent/google_oauth.py` (#19673)
and `tools/mcp_oauth.py` (#21148).
Adds `tests/hermes_cli/test_auth_toctou_file_modes.py` asserting final
file mode 0o600 and parent dir mode 0o700 across all three writers, plus
an explicit `os.open(flags, mode)` check on the main auth.json writer
that would fail if anyone reintroduces the `Path.open('w')` pattern.
POSIX-only (mode bits skipped on Windows).
Flip the default for HERMES_REDACT_SECRETS from off to on so the redactor
already wired into send_message_tool, logs, and tool output actually runs
on a fresh install.
- agent/redact.py: env-var default "" → "true"
- hermes_cli/config.py: DEFAULT_CONFIG security.redact_secrets True;
two config-template comments rewritten
- gateway/run.py + cli.py: startup log / banner warning when the user
has explicitly opted out, so the downgrade is visible in agent.log
and at CLI banner time
- docs/reference/environment-variables.md: description reconciled
- tests: flipped the default-pin, restructured the force=True
regression test to explicit-false instead of unset
Users who need raw credential values (redactor development) can still
opt out via security.redact_secrets: false in config.yaml or
HERMES_REDACT_SECRETS=false in .env.
Closes#17691.
Addresses #20785 (short-term output-pipeline recommendation).
Follow-up on top of @kyan12's PR #20888 — same feature, cleaner shape,
wider coverage.
Changes:
- Drop the synthetic '[System note: ...]' in the internal MessageEvent.
The existing _is_resume_pending branch in _handle_message_with_agent
(run.py ~L13738) already injects a reason-aware recovery system note
on the next turn. With kyan's text in place the model saw two stacked
system notes. Now the event text is empty and the existing injection
path owns the wording.
- Drop SessionStore.list_resume_pending() as a new public method. The
filter is 8 lines inline in _schedule_resume_pending_sessions() —
one caller, no other pluggability need.
- Add 'restart_interrupted' to the auto-resume reason set. That's the
reason SessionStore.suspend_recently_active() stamps on sessions
recovered from a crash/OOM/SIGKILL (no .clean_shutdown marker).
Previously those sessions had to wait for a real user message to
auto-resume; now they continue automatically at startup like
drain-timeout interruptions do.
- Reasons live in a _AUTO_RESUME_REASONS frozenset at class scope so
future reasons (e.g. 'manual_resume_request') can be opted in with
one line.
Test coverage added:
- drain-timeout + crash-recovery both scheduled
- stale entries skipped (outside freshness window)
- suspended entries skipped (suspended > resume_pending)
- originless entries skipped (no routing target)
- disallowed reasons skipped (graceful forward-compat)
E2E verified end-to-end with a real on-disk SessionStore: 2 eligible
sessions scheduled, 2 ineligible skipped, empty-text internal events
delivered to the adapter.
Co-authored-by: Kevin Yan <kevyan1998@gmail.com>
The kanban_heartbeat tool called heartbeat_worker but never
heartbeat_claim, so a worker that loops the tool while a single tool
call blocks the agent for >DEFAULT_CLAIM_TTL_SECONDS still got
reclaimed by release_stale_claims. The function name and
heartbeat_claim's own docstring imply otherwise:
"Workers that know they'll exceed 15 minutes should call this
every few minutes to keep ownership."
But there was no caller in the worker tool path. Workers couldn't
invoke heartbeat_claim themselves either — it isn't exposed as a tool.
Fix: _handle_heartbeat now calls heartbeat_claim first, reading
HERMES_KANBAN_CLAIM_LOCK from the worker env (the dispatcher pins
this in _default_spawn). Falls back to _claimer_id() for locally-
driven workers that didn't go through dispatcher spawn.
Test: tests/tools/test_kanban_tools.py::test_heartbeat_extends_claim_expires
rewinds claim_expires into the past, calls the tool, and asserts the
new value is at least now + DEFAULT_CLAIM_TTL_SECONDS // 2. Verified to
fail against the unfixed code (claim_expires stays at the rewound
value).
Closes the root cause underlying the symptom in #21141 (15-min
respawns of long-running workers). #21141 separately addresses
post-reclaim cleanup; this fixes the upstream "shouldn't have been
reclaimed in the first place" half.
When display.cleanup_progress (or display.platforms.<plat>.cleanup_progress)
is true, the gateway deletes tool-progress bubbles, long-running '⏳ Still
working...' notices, and status-callback messages after the final response
is delivered successfully. Currently effective on adapters that implement
delete_message (Telegram); silently no-ops elsewhere. Off by default.
Failed runs skip cleanup so bubbles stay as breadcrumbs.
Minimal plumbing: base.py's existing post_delivery_callback slot now chains
new registrations onto any existing callback (with per-callback exception
isolation) rather than clobbering. Stale-generation registrations are
rejected so they can't step on a fresher run's callbacks. This lets the
cleanup callback coexist with the background-review release hook already
registered on the same slot.
Co-authored-by: mrcharlesiv <Mrcharlesiv@gmail.com>
The rescan-on-platform-change fix landed in #18739 ships one regression
test that exercises the HERMES_PLATFORM env-var path. Three other code
paths in get_skill_commands / _resolve_skill_commands_platform have no
direct coverage; this commit adds a regression test for each.
- Gateway session context (HERMES_SESSION_PLATFORM via ContextVar): the
resolver consults get_session_env after HERMES_PLATFORM, and the
gateway sets that variable through set_session_vars (a ContextVar),
not os.environ. The test uses set_session_vars / clear_session_vars
to drive the actual gateway signal, and the disabled-skill stub reads
the same value via get_session_env. A regression that swapped
get_session_env for plain os.getenv would still pass an env-var-based
test but break concurrent gateway sessions, which is the bug the
ContextVar plumbing exists to prevent.
- Returning to no-platform-scope (CLI / cron / RL rollouts after a
gateway session): the cached telegram view must be dropped and the
unfiltered scan repopulated when HERMES_PLATFORM is unset again.
- Same-platform cache hit: consecutive calls under the same platform
scope must NOT rescan. The rescan trigger is change in scope, not
"always re-resolve" — a gateway serving many consecutive telegram
requests should pay the scan cost once, not per request.
The third test wraps scan_skill_commands with a spy after the cache is
primed, so the assertion is on call_count == 0 across three subsequent
get_skill_commands() calls.
All 39 tests in tests/agent/test_skill_commands.py pass under
scripts/run_tests.sh.
In native image mode (vision-capable models like gpt-4o, claude-sonnet-4),
build_native_content_parts() previously emitted only the user's caption
plus image_url parts. The local file path of each attached image never
appeared in the conversation text, so the model could see the pixels but
had no string handle for tools that take image_url: str (custom MCP
tools, vision_analyze on a re-look, attach-to-tracker workflows).
The text-mode path already injects an equivalent hint via
Runner._enrich_message_with_vision ("...vision_analyze using image_url:
<path>..."). This brings native mode to parity by appending one
"[Image attached at: <path>]" line per successfully attached image to
the user-text part of the multimodal turn. Skipped (unreadable) paths
are NOT advertised, so the model is never told a non-existent file is
attached.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Issue #17648 added a post-update SIGTERM-survivor sweep to `cmd_update`:
~3s after issuing graceful/SIGTERM restarts, the code re-queries
`find_gateway_pids` and SIGKILLs anything still alive. That's the
right fix for stuck-drain gateways in production, but it broke three
unit tests that assumed `find_gateway_pids` would keep returning the
same PIDs forever:
FAILED ::TestCmdUpdateLaunchdRestart::test_update_restarts_profile_manual_gateways
AssertionError: Expected 'kill' to not have been called. Called 1 times.
Calls: [call(12345, <Signals.SIGKILL: 9>)].
FAILED ::TestCmdUpdateLaunchdRestart::test_update_profile_manual_gateway_falls_back_to_sigterm
AssertionError: Expected 'kill' to have been called once. Called 2 times.
Calls: [call(12345, SIGTERM), call(12345, SIGKILL)].
FAILED ::TestServicePidExclusion::test_update_kills_manual_pid_but_not_service_pid
assert 2 == 1
manual_kills = [call(42999, SIGTERM), call(42999, SIGKILL)]
In each test `os.kill` is mocked, so the simulated PID never actually
exits \u2014 the sweep finds it again and escalates. The production code
is correct; the tests just need to model OS behaviour properly.
Two-test fix (profile-manual restart cases): use
`side_effect=[[12345], []]` so the first `find_gateway_pids` call
returns the live PID and the second (the sweep) returns nothing, as if
the OS had reaped the process.
Service-PID-exclusion fix: track which PIDs got killed in a closure
set, and exclude them on subsequent `fake_find` calls. `os.kill`
gets a `side_effect` that records the kill instead of swallowing it
silently. Now the sweep doesn't re-find the manual PID, no SIGKILL
escalation, `manual_kills == 1`.
Validation:
$ pytest tests/hermes_cli/test_update_gateway_restart.py -q
43 passed in 4.13s
No production code change. Fixes the three failures observed on `main`
(run 25250051126):
test_update_restarts_profile_manual_gateways
test_update_profile_manual_gateway_falls_back_to_sigterm
test_update_kills_manual_pid_but_not_service_pid
Refs: #17648 (post-update survivor sweep that the tests didn't model).
_write_json (the persistence helper used by HermesTokenStorage for both
tokens and client_info) created the temp file via Path.write_text and
only chmod'd it to 0o600 afterward. Between create and chmod the file
existed on disk at the process umask (commonly 0o644 = world-readable),
briefly exposing MCP OAuth access/refresh tokens to other local users.
Use os.open with O_WRONLY|O_CREAT|O_EXCL and an explicit S_IRUSR|S_IWUSR
mode so the file is created atomically at 0o600, plus tighten the parent
dir to 0o700 so siblings can't traverse to the creds file. The temp name
also gains a per-process random suffix to avoid collisions between
concurrent writers and stale leftovers from a crashed prior write.
Mirrors the fix shipped for agent/google_oauth.py in #19673.
Adds a regression test asserting the resulting file mode is 0o600 and
the parent directory is 0o700 (skipped on Windows where POSIX mode bits
aren't enforced).
Two CI tests for the new `--yes` update flag (#18261) flaked under
`pytest-xdist` on Linux/Python 3.11 even though they passed every
local run on macOS/Python 3.14.4:
FAILED tests/hermes_cli/test_update_yes_flag.py
::TestUpdateYesConfigMigration::test_no_yes_flag_still_prompts_in_tty
`AssertionError: assert <MagicMock 'input'>.called is False`
FAILED tests/hermes_cli/test_update_yes_flag.py
::TestUpdateYesStashRestore::test_yes_restores_stash_without_prompting
`AssertionError: assert <MagicMock '_restore_stashed_changes'>.called is False`
Captured stdout for the first failure shows `cmd_update` taking the
"Non-interactive session \u2014 skipping config migration prompt." branch
\u2014 i.e. the `sys.stdin.isatty() and sys.stdout.isatty()` check at
`hermes_cli/main.py:7118` evaluated to `False` despite the test doing:
with patch("hermes_cli.main.sys") as mock_sys:
mock_sys.stdin.isatty.return_value = True
mock_sys.stdout.isatty.return_value = True
The whole-module mock is fragile under xdist worker reuse: a sibling
test that imports `hermes_cli.main` first can leave another `sys`
reference resolved inside the function (re-import in a helper, etc.),
and the wholesale module replacement never gets consulted.
Switch to `patch.object(_sys.stdin, "isatty", return_value=True)` (and
the same for `stdout`). That patches the *attribute on the real stream
object* \u2014 every call site, no matter how it reached `sys.stdin`,
hits the patched method. Same fix applied to the stash-restore test
(it took the "non-TTY \u2192 skip restore prompt" branch for the same reason).
Validation:
$ pytest tests/hermes_cli/test_update_yes_flag.py -q
3 passed in 5.47s
No production code change. Fixes the two failures observed on `main`
(run 25250051126):
`tests/hermes_cli/test_update_yes_flag.py::TestUpdateYesConfigMigration::test_no_yes_flag_still_prompts_in_tty`
`tests/hermes_cli/test_update_yes_flag.py::TestUpdateYesStashRestore::test_yes_restores_stash_without_prompting`
Refs: #18261 (added the `--yes` flag + these tests).
