The clarify tool returned 'not available in this execution context' for
every gateway-mode agent because gateway/run.py never passed
clarify_callback into the AIAgent constructor. Schema actively encouraged
calling it; users never saw the question.
Changes:
- tools/clarify_gateway.py — new event-based primitive mirroring
tools/approval.py: register/wait_for_response/resolve_gateway_clarify
with per-session FIFO, threading.Event blocking with 1s heartbeat
slices (so the inactivity watchdog keeps ticking), and
clear_session for boundary cleanup.
- gateway/platforms/base.py — abstract send_clarify with a numbered-text
fallback so every adapter (Discord, Slack, WhatsApp, Signal, Matrix,
etc.) gets a working clarify out of the box. Plus an active-session
bypass: when the agent is blocked on a text-awaiting clarify, the next
non-command message routes inline to the runner's intercept instead
of being queued + triggering an interrupt. Same shape as the /approve
deadlock fix from PR #4926.
- gateway/platforms/telegram.py — concrete send_clarify renders one
inline button per choice plus '✏️ Other (type answer)'. cl: callback
handler resolves numeric choices immediately, flips to text-capture
mode for Other, with the same authorization guards as exec/slash
approvals.
- gateway/run.py — clarify_callback wired at the cached-agent per-turn
callback assignment site (only the user-facing agent path; cron and
hygiene-compress agents have no human attached). Bridges sync→async
via run_coroutine_threadsafe, blocks with the configured timeout, and
returns a '[user did not respond within Xm]' sentinel on timeout so
the agent adapts rather than pinning the running-agent guard. Text-
intercept added to _handle_message before slash-confirm intercept
(skipping slash commands). clear_session called in the run's finally
to cancel any orphan entries.
- hermes_cli/config.py — agent.clarify_timeout default 600s.
- website/docs/user-guide/messaging/telegram.md — Interactive Prompts
section.
Tests:
- tests/tools/test_clarify_gateway.py (14 tests) — full primitive
coverage: button resolve, open-ended auto-await, Other flip, timeout
None, unknown-id idempotency, clear_session cancellation, FIFO
ordering, register/unregister notify, config default.
- tests/gateway/test_telegram_clarify_buttons.py (12 tests) — render
paths (multi-choice/open-ended/long-label/HTML-escape/not-connected),
callback dispatch (numeric resolve/Other flip/already-resolved/
unauthorized/invalid-token), and base-adapter text fallback.
Out of scope: bot-to-bot, guest mode, checklists, poll media, live
photos. Closes#24191.
* feat(lsp): semantic diagnostics from real language servers in write_file/patch
Wire ~26 language servers (pyright, gopls, rust-analyzer, typescript-language-server,
clangd, bash-language-server, ...) into the post-write lint check used by write_file
and patch. The model now sees type errors, undefined names, missing imports, and
project-wide semantic issues introduced by its edits, not just syntax errors.
LSP is gated on git workspace detection: when the agent's cwd or the file being
edited is inside a git worktree, LSP runs against that workspace; otherwise the
existing in-process syntax checks are the only tier. This keeps users on
user-home cwds (Telegram/Discord gateway chats) from spawning daemons.
The post-write check is layered: in-process syntax check first (microseconds),
then LSP semantic diagnostics second when syntax is clean. Diagnostics are
delta-filtered against a baseline captured at write start, so the agent only
sees errors its edit introduced. A flaky/missing language server can never
break a write -- every LSP failure path falls back silently to the syntax-only
result.
New module agent/lsp/ split into:
- protocol.py: Content-Length JSON-RPC framer + envelope helpers
- client.py: async LSPClient (spawn, initialize, didOpen/didChange,
ContentModified retry, push/pull diagnostic stores)
- workspace.py: git worktree walk-up + per-server NearestRoot resolver
- servers.py: registry of 26 language servers (extension match,
root resolver, spawn builder per language)
- install.py: auto-install dispatch (npm install --prefix, go install
with GOBIN, pip install --target) into HERMES_HOME/lsp/bin/
- manager.py: LSPService (per-(server_id, root) client registry, lazy
spawn, broken-set, in-flight dedupe, sync facade for tools layer)
- reporter.py: <diagnostics> block formatter (severity-1-only, 20-per-file)
- cli.py: hermes lsp {status,list,install,install-all,restart,which}
Wired into tools/file_operations.py:
- write_file/patch_replace now call _snapshot_lsp_baseline before write
- _check_lint_delta gains a third tier: LSP semantic diagnostics when
syntax is clean
- All LSP code paths swallow exceptions; write_file's contract unchanged
Config: 'lsp' section in DEFAULT_CONFIG with enabled (default true),
wait_mode, wait_timeout, install_strategy (default 'auto'), and per-server
overrides (disabled, command, env, initialization_options).
Tests: tests/agent/lsp/ -- 49 tests covering protocol framing (encode and
read_message round-trip, EOF/truncation/missing Content-Length), workspace
gate (git walk-up, exclude markers, fallback to file location), reporter
(severity filter, max-per-file cap, truncation), service-level delta filter,
and an in-process mock LSP server that exercises the full client lifecycle
including didChange version bumps, dedup, crash recovery, and idempotent
teardown.
Live E2E verified end-to-end through ShellFileOperations: pyright
auto-installed via npm into HERMES_HOME, baseline captured, type error
introduced, single delta diagnostic surfaced with correct line/column/code/
source, then patch fix removes the diagnostic from the output.
Docs: new website/docs/user-guide/features/lsp.md page covering supported
languages, configuration knobs, performance characteristics, and
troubleshooting; cli-commands.md updated with the 'hermes lsp' reference;
sidebar updated.
* feat(lsp): structured logging, backend gate, defensive walk caps
Cherry-picks the substantive ideas from #24155 (different scope, same
problem space) onto our PR.
agent/lsp/eventlog.py (new): dedicated structured logger
``hermes.lint.lsp`` with steady-state silence. Module-level dedup sets
keep a 1000-write session at exactly ONE INFO line ("active for
<root>") at the default INFO threshold; clean writes log at DEBUG so
they never reach agent.log under normal config. State transitions
(server starts, no project root for a file, server unavailable) fire
at INFO/WARNING once per (server_id, key); novel events (timeouts,
unexpected errors) fire WARNING per call. Grep recipe: ``rg 'lsp\\['``.
agent/lsp/manager.py: wire the eventlog into _get_or_spawn and
get_diagnostics_sync so users can answer "did LSP fire on this edit?"
with a single grep, plus surface "binary not on PATH" warnings once
instead of silently retrying every write.
tools/file_operations.py: backend-type gate. ``_lsp_local_only()``
returns False for non-local backends (Docker / Modal / SSH /
Daytona); ``_snapshot_lsp_baseline`` and ``_maybe_lsp_diagnostics``
now skip entirely on remote envs. The host-side language server
can't see files inside a sandbox, so this prevents pretending to
lint a file the host process can't open.
agent/lsp/protocol.py: 8 KiB cap on the header block in
``read_message``. A pathological server that streams headers
without ever emitting CRLF-CRLF would have looped forever consuming
bytes; now raises ``LSPProtocolError`` instead.
agent/lsp/workspace.py: 64-step cap on ``find_git_worktree`` and
``nearest_root`` upward walks, plus try/except containment around
``Path(...).resolve()`` and child ``.exists()`` calls. Defensive
against pathological inputs (symlink loops, encoding errors,
permission failures mid-walk) — the lint hook is hot-path code and
must never raise.
Tests:
- tests/agent/lsp/test_eventlog.py: 18 tests covering steady-state
silence (clean writes stay DEBUG), state-transition INFO-once
semantics (active for, no project root), action-required
WARNING-once (server unavailable), per-call WARNING (timeouts,
spawn failures), and the "1000 clean writes => 1 INFO" contract.
- tests/agent/lsp/test_backend_gate.py: 5 tests verifying
_lsp_local_only / snapshot_baseline / maybe_lsp_diagnostics skip
the LSP layer for non-local backends and route correctly for
LocalEnvironment.
- tests/agent/lsp/test_protocol.py: new test_read_message_rejects_runaway_header
exercising the 8 KiB cap.
Validation:
- 73/73 LSP tests pass (49 original + 18 eventlog + 5 backend-gate + 1 framer cap)
- 198/198 pass when run alongside existing file_operations tests
- Live E2E re-run with pyright still surfaces "ERROR [2:12] Type
... reportReturnType (Pyright)" through the full path, then patch
fix removes it on the next call.
* feat(lsp): atexit cleanup + separate lsp_diagnostics JSON field
Two improvements salvaged from #24414's plugin-form alternative,
keeping our core-integrated design:
1. atexit cleanup of spawned language servers
----------------------------------------------------------------
``agent/lsp/__init__.get_service`` now registers an ``atexit``
handler on first creation that tears down the LSPService on
Python exit. Without this, every ``hermes chat`` exit was
leaking pyright/gopls/etc. processes for a few seconds while
their stdout buffers drained -- they got reaped by the kernel
eventually but a watchful ``ps aux`` would catch them.
The handler runs once per process (gated by
``_atexit_registered``); idempotent ``shutdown_service``
ensures double-fire is a no-op. Errors during shutdown are
swallowed at debug level since by the time atexit fires the
user has already seen the agent's final response.
2. Separate ``lsp_diagnostics`` field on WriteResult / PatchResult
----------------------------------------------------------------
Previously the LSP layer folded its diagnostic block into the
``lint.output`` string, conflating the syntax-check tier with
the semantic tier. The agent (and any downstream parsers) now
read syntax errors and semantic errors as independent signals:
{
"bytes_written": 42,
"lint": {"status": "ok", "output": ""},
"lsp_diagnostics": "<diagnostics file=...>\nERROR [2:12] ..."
}
``_check_lint_delta`` returns to its original two-tier shape
(syntax check + delta filter); ``write_file`` and
``patch_replace`` independently fetch LSP diagnostics via
``_maybe_lsp_diagnostics`` and pass them into the new field.
``patch_replace`` propagates the inner write_file's
``lsp_diagnostics`` so the outer PatchResult carries the patch's
delta correctly.
Tests: 19 new
- tests/agent/lsp/test_lifecycle.py (8 tests): atexit registration
fires once and only once across N get_service calls; the
registered callable is our internal shutdown wrapper;
shutdown_service is idempotent and safe when never started;
exceptions during shutdown are swallowed; inactive service is
cached so we don't rebuild on every check.
- tests/agent/lsp/test_diagnostics_field.py (11 tests): WriteResult
/ PatchResult dataclass shape, to_dict include/omit semantics,
channel separation (lint and lsp_diagnostics carry independent
signals), write_file populates the field via
_maybe_lsp_diagnostics only when the syntax tier is clean,
patch_replace propagates the field forward from its internal
write_file.
Validation:
- 92/92 LSP tests pass (73 prior + 8 lifecycle + 11 diagnostics field)
- 217/217 pass with file_operations + LSP combined
- Live E2E reverified: clean writes -> both fields empty/none; type
error introduced -> lint clean (parses), lsp_diagnostics carries
the pyright reportReturnType block; patch fix -> both fields
clean again.
* fix(lsp): broken-set short-circuit so a wedged server isn't paid every write
Discovered while auditing failure paths: a language server binary that
hangs (sleep forever, no LSP traffic on stdin/stdout) caused EVERY
subsequent write to re-pay the 8s snapshot_baseline timeout. Five
writes = ~64s of dead time.
The bug: ``_get_or_spawn`` adds the (server_id, root) pair to
``_broken`` inside its inner exception handler, but when the OUTER
``_loop.run`` timeout fires, it cancels the inner task before that
handler runs. The pair never makes it to broken-set, so the next
write re-enters the spawn path and re-pays the timeout.
Fix:
- New ``_mark_broken_for_file`` helper at the service layer marks
the (server_id, workspace_root) pair broken from the OUTSIDE when
the outer timeout fires. Called from the except branches in
``snapshot_baseline``, ``get_diagnostics_sync`` (asyncio.TimeoutError
+ generic Exception). Also kills any orphan client process that
survived the cancelled future, fire-and-forget with a 1s ceiling.
- ``enabled_for`` now consults the broken-set BEFORE returning True.
Files in already-broken (server_id, root) pairs short-circuit to
False, so the file_operations layer skips the LSP path entirely
with no spawn cost. Until the service is restarted (``hermes lsp
restart``) or the process exits.
- A single eventlog WARNING is emitted on first mark-broken so the
user knows which server gave up. Subsequent edits in the same
project stay silent.
Tests: 7 new in tests/agent/lsp/test_broken_set.py — covers the
key shape (server_id, per_server_root), enabled_for short-circuit,
sibling-file skip in same project, project isolation (broken in
A doesn't affect B), graceful no-op for missing-server / no-workspace,
and an end-to-end test that snapshots after a failure and verifies
the next ``enabled_for`` returns False.
Validation:
- Live retest of the wedged-binary scenario: 5 sequential writes,
first 8.88s (the one snapshot timeout), subsequent four ~0.84s
(no LSP cost). Down from 5x12.85s = 64s before this fix.
- 99/99 LSP tests pass (92 prior + 7 broken-set)
- 224/224 pass with file_operations + LSP combined
- Happy path E2E reverified — clean write, type error introduced,
patch fix all behave correctly with the new broken-set logic.
Note: the FIRST write to a wedged binary still pays 8s (the
snapshot_baseline timeout). We could shorten that, but pyright/
tsserver normally take 2-3s and slow CI rust-analyzer can need
5+ seconds, so 8s is the conservative ceiling. Subsequent writes
are instant.
Allow integrations to share a visible Camofox identity with Hermes and recover existing tabs without carrying local patches.
Co-authored-by: Cursor <cursoragent@cursor.com>
Detect when write_file / patch calls fail during a turn and are never
superseded by a successful write to the same path. When the final
text response is delivered, append an advisory footer listing the
files that did NOT change — so models that over-claim 'patched 5 files'
after 4 silent failures can't hide the lie.
Catches the failure mode reported in Ben Eng's llm-wiki session:
grok-4.1-fast issued batches of parallel patches, half failed with
'Could not find old_string', and the agent summarised the turn
claiming every file was edited. The user had to manually run
'git status' each turn to catch it.
The verifier is a pure post-hoc check on tool results — no new LLM
calls, no synthetic messages injected into history (prompt cache
preserved), no changes to tool argument dispatch. Per-turn state is
keyed by path; a later successful write to the same path clears the
failure entry so single-file retry recovery is not flagged.
Wired into both _execute_tool_calls_concurrent and
_execute_tool_calls_sequential, so batched parallel patches and one-at-
a-time edits are both covered. Footer emission happens after the
agent loop exits, before transform_llm_output / post_llm_call plugin
hooks run, so plugins still see (and can modify) the augmented text.
Config: display.file_mutation_verifier (bool, default true) +
HERMES_FILE_MUTATION_VERIFIER env override.
31 unit tests in tests/run_agent/test_file_mutation_verifier.py cover
target extraction (write_file, patch-replace, patch-v4a single and
multi-file), error-preview extraction (JSON .error field and plain
string), per-turn state transitions (first-error-wins on repeated
failure, success supersedes failure), footer rendering (truncation
at 10 entries, user-actionable hint), and env/config precedence.
Companion docs updated: user-guide/configuration.md +
reference/environment-variables.md.
* feat(security): supply-chain advisory checker + lazy-install framework + tiered install fallback
Three coordinated mitigations for the Mini Shai-Hulud worm hitting
mistralai 2.4.6 on PyPI (2026-05-12) and for the next single-package
compromise that follows.
# What this PR makes true
1. Users with the poisoned mistralai 2.4.6 in their venv get a loud
detection banner with copy-pasteable remediation steps the moment
they run hermes (and on every gateway startup).
2. One quarantined / yanked PyPI package can no longer silently demote
a fresh install to 'core only' — the installer keeps every other
extra and tells the user which tier landed.
3. Future opt-in backends (Mistral, ElevenLabs, Honcho, etc.) can
lazy-install on first use under a strict allowlist, instead of
eagerly pulling everything at install time.
# Detection: hermes_cli/security_advisories.py
- ADVISORIES catalog (one entry currently: shai-hulud-2026-05 for
mistralai==2.4.6). Adding the next one is a single dataclass.
- detect_compromised() uses importlib.metadata.version() — no pip
dependency, works in uv venvs that lack pip.
- Banner cache (~/.hermes/cache/advisory_banner_seen) rate-limits
the startup banner to once per 24h per advisory.
- Acks persisted to security.acked_advisories in config.yaml; never
re-banner after ack.
- Wired into:
* hermes doctor — runs first, prints full remediation block
* hermes doctor --ack <id> — dismisses an advisory
* cli.py interactive run() and single-query branches — short
stderr banner pointing at hermes doctor
* gateway/run.py startup — operator-visible warning in gateway.log
# Lazy-install framework: tools/lazy_deps.py
- LAZY_DEPS allowlist maps namespaced feature keys (tts.elevenlabs,
memory.honcho, provider.bedrock, etc.) to pip specs.
- ensure(feature) installs missing deps in the active venv via the
uv → pip → ensurepip ladder (matches tools_config._pip_install).
- Strict spec safety regex rejects URLs, file paths, shell metas,
pip flag injection, control chars — only PyPI-by-name accepted.
- Gated on security.allow_lazy_installs (default true) plus the
HERMES_DISABLE_LAZY_INSTALLS env var for restricted/audited envs.
- Migrated three backends as proof of pattern:
* tools/tts_tool.py — _import_elevenlabs() calls ensure first
* plugins/memory/honcho/client.py — get_honcho_client lazy-installs
* tts.mistral / stt.mistral entries pre-registered for when PyPI
restores mistralai
# Installer fallback tiers
scripts/install.sh, scripts/install.ps1, setup-hermes.sh:
- Centralised _BROKEN_EXTRAS list (currently: mistral). Edit one
array when a transitive breaks; users keep every other extra.
- New 'all minus known-broken' tier between [all] and the existing
PyPI-only-extras tier. Only kicks in when [all] fails resolve.
- All three tiers explicit: every fallback announces which tier
landed and prints a re-run hint when not on Tier 1.
- install.ps1 and install.sh both regenerate their tier specs from
the same _BROKEN_EXTRAS array so updates stay in sync.
Side effect: install.ps1 Tier 2 spec previously hardcoded 'mistral'
in its extra list — bug fixed by the refactor (mistral is filtered
out).
# Config
hermes_cli/config.py — DEFAULT_CONFIG.security gains:
- acked_advisories: [] (advisory IDs the user has dismissed)
- allow_lazy_installs: True (security gate for ensure())
No config version bump needed — both keys nest under existing
security: block, and load_config's deep-merge picks up DEFAULT_CONFIG
defaults for users with older configs.
# Tests
tests/hermes_cli/test_security_advisories.py — 23 tests covering:
- detect_compromised matches/non-matches, wildcard frozenset
- ack persistence, idempotence, blank rejection, config-failure path
- banner cache rate limiting + 24h re-banner + ack-stops-banner
- short_banner_lines / full_remediation_text / render_doctor_section /
gateway_log_message
- shipped catalog well-formedness invariant
tests/tools/test_lazy_deps.py — 40 tests covering:
- spec safety: 11 safe parametrized + 18 unsafe parametrized
- allowlist: unknown-feature rejection, namespace.name shape,
every shipped spec passes the safety regex
- security gating: config flag, env var, default, fail-open
- ensure() happy/sad paths: already-satisfied, install success,
pip stderr surfaced on failure, install-succeeds-but-still-missing
- is_available, feature_install_command
Combined: 63 new tests, all passing under scripts/run_tests.sh.
# Validation
- scripts/run_tests.sh tests/hermes_cli/test_security_advisories.py
tests/tools/test_lazy_deps.py → 63/63 passing
- scripts/run_tests.sh tests/hermes_cli/test_doctor.py
tests/hermes_cli/test_doctor_command_install.py
tests/tools/test_tts_mistral.py tests/tools/test_transcription_tools.py
tests/tools/test_transcription_dotenv_fallback.py → 165/165 passing
- scripts/run_tests.sh tests/hermes_cli/ tests/tools/ →
9191 passed, 8 pre-existing failures (verified on origin/main
before this change)
- bash -n on install.sh and setup-hermes.sh → OK
- py_compile on all modified .py files → OK
- End-to-end smoke test of detect_compromised + render_doctor_section
+ gateway_log_message with mocked installed version → produces
copy-pasteable remediation output
# Community
Full advisory + remediation steps:
website/docs/community/security-advisories/shai-hulud-mistralai-2026-05.md
Short-form post drafts (Discord, GitHub pinned issue, README banner):
scripts/community-announcement-shai-hulud.md
Refs: PR #24205 (mistral disabled), Socket Security advisory
<https://socket.dev/blog/mini-shai-hulud-worm-pypi>
* build(deps): pin every direct dep to ==X.Y.Z (no ranges)
Companion to the supply-chain advisory work: replace every >=/</~= range
in pyproject.toml's [project.dependencies] and [project.optional-dependencies]
with an exact ==X.Y.Z pin sourced from uv.lock.
Why: ranges allow PyPI to ship a fresh version of any direct dep at any
time without a code review on our side. With ranges, the malicious
mistralai 2.4.6 release would have been pulled by every fresh
'pip install -e .[all]' for the hours between upload and PyPI's
quarantine — exactly the install window we got hit on. Exact pins close
that window: the only way a new package version reaches a user is via
an intentional update on our end.
What the user-facing change is: nothing, behavior-wise. Every package
resolves to the same version it was already resolving to via uv.lock —
the pins just remove the resolver's freedom to pick a different one.
Cost: any user installing Hermes alongside another package that requires
a newer pin gets a resolver conflict. Acceptable for our isolated-venv
install path; documented in the new comment block.
Build-system requires line (setuptools>=61.0) is intentionally left
as a range — pinning the build backend would block fresh pip from
bootstrapping the build on architectures where that exact wheel isn't
available.
mistral extra (mistralai==2.3.0) is pinned but stays out of [all]
(per PR #24205). 'uv lock' regeneration will fail until PyPI restores
mistralai; lockfile regeneration is gated behind that, NOT on every PR.
LAZY_DEPS in tools/lazy_deps.py also moved to exact pins so the lazy-
install pathway can never resolve a different version than the one
declared in pyproject.toml.
Validation:
- Cross-checked all 77 pinned direct deps in pyproject.toml against
uv.lock — every pin matches the resolved version exactly.
- Cross-checked all LAZY_DEPS specs against uv.lock — same.
- 'uv pip install -e .[all] --dry-run' resolves 205 packages cleanly.
- tests/tools/test_lazy_deps.py + tests/hermes_cli/test_security_advisories.py
→ 63/63 passing (every shipped spec passes the safety regex).
- Doctor + TTS + transcription targeted suite → 146/146 passing.
* build(deps): hash-verify transitives via uv.lock; remove unresolvable [mistral] extra
You asked: 'what about the dependencies the dependencies rely on?' —
correctly noting that exact-pinning direct deps in pyproject.toml does
NOT cover the transitive graph. `pip install` and `uv pip install` both
re-resolve transitives fresh from PyPI at install time, so a compromised
transitive (e.g. `httpcore` if it got worm-poisoned tomorrow) would
still hit our users even with every direct dep exact-pinned.
# What this commit fixes
1. **Both real installer scripts now prefer `uv sync --locked` as Tier 0.**
uv.lock records SHA256 hashes for every transitive — a compromised
package with a different hash gets REJECTED. Falls through to the
existing `uv pip install` cascade if the lockfile is missing or
stale, with a loud warning that the fallback path does NOT
hash-verify transitives. Previously only `setup-hermes.sh` (the dev
path) used the lockfile; `scripts/install.sh` and `scripts/install.ps1`
(the paths fresh users actually run) skipped it.
2. **Removed the `[mistral]` extra entirely.** The `mistralai` PyPI
project is fully quarantined right now — every version returns 404,
so any pin we wrote was unresolvable, which broke `uv lock --check`
in CI. Restoration is documented in pyproject.toml as a 5-step
checklist (verify, re-add extra, re-enable in 4 modules, regenerate
lock, optionally re-add to [all]).
3. **Regenerated uv.lock.** 262 packages, mistralai/eval-type-backport/
jsonpath-python pruned. `uv lock --check` now passes.
# Defense-in-depth view
| Layer | Where | Protects against |
|----------------------------|-------------------|-------------------------------------------|
| Exact pins in pyproject | direct deps | new mistralai 2.4.6-style direct compromise |
| uv.lock + `--locked` install | transitive graph | transitive worm injection |
| Tier-0 hash-verified path | install.sh / .ps1 | actually USE the lockfile in fresh installs |
| `uv lock --check` CI gate | every PR | drift between pyproject and lockfile |
| `hermes_cli/security_advisories.py` | runtime | cleanup for users who already got hit |
The exact pinning + hash verification together close the supply-chain
gap. Without the lockfile path, exact pins alone are theater.
# Validation
- `uv lock --check` → passes (262 packages resolved, no drift).
- `bash -n` on install.sh + setup-hermes.sh → OK.
- 209/209 tests passing across new + adjacent test files
(test_lazy_deps.py, test_security_advisories.py, test_doctor.py,
test_tts_mistral.py, test_transcription_tools.py).
- TOML parse OK.
* chore: remove community announcement drafts (PR body covers it)
* build(deps): lazy-install every opt-in backend (anthropic, search, terminal, platforms, dashboard)
Extends the lazy-install framework to cover everything that's not used by
every hermes session. Base install drops from ~60 packages to 45.
Moved out of core dependencies = []:
- anthropic (only when provider=anthropic native, not via aggregators)
- exa-py, firecrawl-py, parallel-web (search backends; only when picked)
- fal-client (image gen; only when picked)
- edge-tts (default TTS but still optional)
New extras in pyproject.toml: [anthropic] [exa] [firecrawl] [parallel-web]
[fal] [edge-tts]. All added to [all].
New LAZY_DEPS entries: provider.anthropic, search.{exa,firecrawl,parallel},
tts.edge, image.fal, memory.hindsight, platform.{telegram,discord,matrix},
terminal.{modal,daytona,vercel}, tool.dashboard.
Each import site now calls ensure() before importing the SDK. Where the
module had a top-level try/except (telegram, discord, fastapi), the
graceful-fallback pattern was extended to lazy-install on first
check_*_requirements() call and re-bind module globals.
Updated test_windows_native_support.py tzdata check from snapshot
(>=2023.3 literal) to invariant (any version + win32 marker).
Validation:
- Base install: 45 packages (was ~60); 6 newly-extracted packages absent
- uv lock --check: passes (262 packages, no drift)
- 209/209 lazy_deps + advisory + doctor + tts/transcription tests passing
- py_compile clean on all 12 modified modules
Cuts input cost for first-turn Claude requests by ~85-90% on subsequent
sessions within an hour. Tools array (~13k tokens for default toolset) +
stable system prefix (~5-8k tokens) get a 1h cache_control marker; the
volatile suffix (memory, USER profile, timestamp, session id) sits in a
separate non-cached block at the end so it doesn't poison the cross-session
prefix when it changes.
Provider gate: Claude on native Anthropic (incl. OAuth subscription),
OpenRouter, and Nous Portal (which proxies to OpenRouter). All other
providers keep today's system_and_3 layout unchanged.
Layout (4 cache_control breakpoints, Anthropic max):
1. tools[-1] -> 1h (cross-session)
2. system content[0] -> 1h (cross-session, stable prefix)
3. messages[-2] -> 5m (within-session rolling)
4. messages[-1] -> 5m (within-session rolling)
Within-session rolling shrinks from 3 messages to 2 to free the breakpoint
budget. On Claude with realistic tool loadouts the long-lived tier carries
the bulk of cross-session value anyway.
System prompt is now always assembled cache-friendly: stable identity /
guidance / skills / platform hints first, then session-stable context
files (AGENTS.md, .cursorrules), then per-call volatile content. Old
single-string callers see the same logical content (same join order),
just reordered so volatile lives at the end.
Config knobs (defaults shown):
prompt_caching:
cache_ttl: "5m" # rolling-window TTL (unchanged)
long_lived_prefix: true # opt-out switch
long_lived_ttl: "1h" # cross-session prefix TTL
Live E2E (tests/agent/test_prompt_caching_live.py, gated on
OPENROUTER_API_KEY) on anthropic/claude-haiku-4.5 with default toolset:
Call 1 (cold): cache_write=13,415 cache_read=0
Call 2 (NEW agent + msg): cache_write=391 cache_read=13,025
Cross-session reuse: 97.09%
Implementation:
* agent/prompt_caching.py: new apply_anthropic_cache_control_long_lived()
+ mark_tools_for_long_lived_cache(); existing apply_anthropic_cache_control()
preserved verbatim for the fallback path.
* agent/anthropic_adapter.py: convert_tools_to_anthropic() now forwards
cache_control onto each Anthropic-format tool dict.
* run_agent.py: _build_system_prompt_parts() returns the 3-tier dict;
_build_system_prompt() joins them (backward compatible).
_supports_long_lived_anthropic_cache() policy added next to the existing
_anthropic_prompt_cache_policy() (which now also recognises Nous Portal
Claude — pre-existing gap fixed in passing).
_build_api_kwargs() resolves tools_for_api once and propagates the
marker through all four build paths (anthropic_messages, bedrock,
codex_responses, profile/legacy chat completions).
Long-lived flag plumbed into the runtime snapshot/restore + model-switch
+ fallback-promotion paths.
Tests:
* tests/agent/test_prompt_caching.py: +8 tests (TestMarkToolsForLongLivedCache,
TestApplyAnthropicCacheControlLongLived).
* tests/run_agent/test_anthropic_prompt_cache_policy.py: +9 tests
(TestSupportsLongLivedAnthropicCache matrix across 8 endpoint classes
+ a fallback-target case).
* tests/agent/test_prompt_caching_live.py: new live E2E (skipif when
OPENROUTER_API_KEY is unset; runs outside the hermetic suite).
* Targeted suites: 327/327 pass (caching/adapter/policy/builder).
* tests/agent/ + tests/run_agent/: 3992 pass, 17 skip, 1 pre-existing
flake (test_async_httpx_del_neuter::test_same_key_replaces_stale_loop_entry,
verified failing on pristine origin/main).
Replace with for all literal-tuple
membership tests. Set lookup is O(1) vs O(n) for tuple — consistent
micro-optimization across the codebase.
608 instances fixed via `ruff --fix --unsafe-fixes`, 0 remaining.
133 files, +626/-626 (net zero).
Two independent opt-in QoL toggles, both off by default.
terminal.docker_extra_args:
- List of extra flags appended verbatim to docker run after security
defaults. Useful for adding capabilities (e.g. --cap-add SETUID) or
other docker run options not exposed by existing config keys.
- Non-string entries are logged and skipped.
- Also available via TERMINAL_DOCKER_EXTRA_ARGS='[...]' env var.
display.timestamps:
- Appends [HH:MM] to user input bullet and the assistant response box
header. Single hub in _format_submitted_user_message_preview()
covers both single-line and multi-line user previews; assistant
response label gets the timestamp at box-open time.
Closes#1569 (timestamps).
Co-authored-by: Mibayy <Mibayy@users.noreply.github.com>
A YAML parse error in ~/.hermes/config.yaml caused load_config() to print
one line to stdout (Warning: Failed to load config: ...) and silently fall
back to DEFAULT_CONFIG, dropping every user override (auxiliary providers,
fallback chain, model settings). Users only noticed when downstream
behavior misbehaved — see issue #23570 where a tab-indent error in the
auxiliary section caused aux fallback to use OpenRouter (depleted) instead
of the configured Codex/MiniMax chain.
Now: log at WARNING (so 'hermes logs' surfaces it), write a prominent line
to stderr, dedup on (path, mtime_ns, size) so concurrent loads don't spam,
and re-warn after the user edits the file. Both call sites (raw read +
merged load) route through the same helper.
Refs #23570
Problem: terminal.docker_env set in config.yaml was silently ignored.
Docker containers never received the user-specified env vars.
Root cause: docker_env was missing from all three config→env bridging
maps (cli.py env_mappings, gateway/run.py _terminal_env_map,
hermes_cli/config.py _config_to_env_sync) and from the terminal_tool
_get_env_config() reader. _create_environment() consumed the key from
container_config correctly, but it was always {} because TERMINAL_DOCKER_ENV
was never set.
Also extend the list-serialisation branches in cli.py and gateway/run.py
to handle dict values via json.dumps (lists already used json.dumps;
plain str() on a dict produces undecodable output).
Fix:
- cli.py: add "docker_env": "TERMINAL_DOCKER_ENV" to env_mappings;
serialise dict values with json.dumps alongside existing list path
- gateway/run.py: same additions to _terminal_env_map and serialisation
- hermes_cli/config.py: add "terminal.docker_env": "TERMINAL_DOCKER_ENV"
to _config_to_env_sync so `hermes config set terminal.docker_env …`
persists to .env correctly
- tools/terminal_tool.py: add docker_env key to _get_env_config() reading
TERMINAL_DOCKER_ENV via _parse_env_var with default "{}"
Tests: add test_docker_env_is_bridged_everywhere to
tests/tools/test_terminal_config_env_sync.py — stash-verified: fails on
origin/main, passes with fix.
Fixes#20537
The plumbing for setting OpenRouter provider preferences and the Pareto Code
router on auxiliary tasks already exists — auxiliary.<task>.extra_body is
forwarded verbatim by call_llm() / async_call_llm(). It just wasn't documented,
so users who wanted (e.g.) Pareto Code routing for compression but the strongest
coder for the main agent had no way to discover the escape hatch.
- hermes_cli/config.py: expand the auxiliary section header with a YAML
example showing provider routing plus plugins under extra_body, and an
explicit note that main-agent provider_routing / openrouter.min_coding_score
do NOT propagate to aux calls (each task is independent by design)
- website/docs/user-guide/configuration.md: new 'OpenRouter routing and
Pareto Code for auxiliary tasks' subsection with worked example
- website/docs/integrations/providers.md: cross-link from the Pareto Code
Router section to the aux-side doc
E2E verified that auxiliary.<task>.extra_body reaches the OpenRouter API with
the configured provider routing and plugins blocks intact.
Pick openrouter/pareto-code as your model and OpenRouter auto-routes each
request to the cheapest model meeting your coding-quality bar (ranked by
Artificial Analysis). The new openrouter.min_coding_score config key (0.0-1.0,
default 0.65) tunes the floor.
- hermes_cli/models.py: add openrouter/pareto-code to OPENROUTER_MODELS so
it shows up in the picker with a description
- hermes_cli/config.py: add openrouter.min_coding_score (default 0.65 — lands
on a mid-tier coder on the current Pareto frontier)
- plugins/model-providers/openrouter: emit extra_body.plugins =
[{id: pareto-router, min_coding_score: X}] when model is openrouter/pareto-code
AND the score is a valid float in [0.0, 1.0]
- agent/transports/chat_completions.py: same emission on the legacy flag
path (when no provider profile is loaded)
- run_agent.py: openrouter_min_coding_score kwarg + storage; plumbed into
both build_kwargs() invocations and the context-summary extra_body path
- cli.py: read openrouter.min_coding_score once at init, validate float in
[0,1], pass to AIAgent constructions (CLI + background-task paths)
- cron/scheduler.py, batch_runner.py, tools/delegate_tool.py,
tui_gateway/server.py: propagate the kwarg (mirrors providers_order
plumbing — subagents inherit, cron/batch read from config)
- tests: profile-level + transport-level coverage of the model gating,
unset/empty/out-of-range handling, and the legacy flag path
- docs: new 'OpenRouter Pareto Code Router' section in providers.md
Verified end-to-end against api.openrouter.ai: at score=0.65 we land on a
mid-tier coder, at omission we get the strongest. Score is silently dropped
on any model other than openrouter/pareto-code, so it's safe to leave set.
/clear, /new, /reset, and /undo now ask the user to confirm before
discarding conversation state — three-option prompt routed through the
existing tools.slash_confirm primitive.
Native yes/no buttons render on Telegram, Discord, and Slack (their
adapters already implement send_slash_confirm); other platforms get a
text-fallback prompt and reply with /approve, /always, or /cancel.
The classic prompt_toolkit CLI uses the same three-option flow via the
established _prompt_text_input pattern (see _confirm_and_reload_mcp).
TUI keeps its existing modal overlay (#12312).
Gated by new config key approvals.destructive_slash_confirm (default
true). Picking 'Always Approve' flips the gate to false so subsequent
destructive commands run silently — matches the established
mcp_reload_confirm UX.
Out of scope: /cron remove (separate domain — scheduled jobs, not
session history). Existing TUI overlay env-var (HERMES_TUI_NO_CONFIRM)
left unchanged; cosmetic unification can come later.
Closes#4069.
## Why
Hermes supports Linux, macOS, and native Windows, but the codebase grew up
POSIX-first and has accumulated patterns that silently break (or worse,
silently kill!) on Windows:
- `os.kill(pid, 0)` as a liveness probe — on Windows this maps to
CTRL_C_EVENT and broadcasts Ctrl+C to the target's entire console
process group (bpo-14484, open since 2012).
- `os.killpg` — doesn't exist on Windows at all (AttributeError).
- `os.setsid` / `os.getuid` / `os.geteuid` — same.
- `signal.SIGKILL` / `signal.SIGHUP` / `signal.SIGUSR1` — module-attr
errors at runtime on Windows.
- `open(path)` / `open(path, "r")` without explicit encoding= — inherits
the platform default, which is cp1252/mbcs on Windows (UTF-8 on POSIX),
causing mojibake round-tripping between hosts.
- `wmic` — removed from Windows 10 21H1+.
This commit does three things:
1. Makes `psutil` a core dependency and migrates critical callsites to it.
2. Adds a grep-based CI gate (`scripts/check-windows-footguns.py`) that
blocks new instances of any of the above patterns.
3. Fixes every existing instance in the codebase so the baseline is clean.
## What changed
### 1. psutil as a core dependency (pyproject.toml)
Added `psutil>=5.9.0,<8` to core deps. psutil is the canonical
cross-platform answer for "is this PID alive" and "kill this process
tree" — its `pid_exists()` uses `OpenProcess + GetExitCodeProcess` on
Windows (NOT a signal call), and its `Process.children(recursive=True)`
+ `.kill()` combo replaces `os.killpg()` portably.
### 2. `gateway/status.py::_pid_exists`
Rewrote to call `psutil.pid_exists()` first, falling back to the
hand-rolled ctypes `OpenProcess + WaitForSingleObject` dance on Windows
(and `os.kill(pid, 0)` on POSIX) only if psutil is somehow missing —
e.g. during the scaffold phase of a fresh install before pip finishes.
### 3. `os.killpg` migration to psutil (7 callsites, 5 files)
- `tools/code_execution_tool.py`
- `tools/process_registry.py`
- `tools/tts_tool.py`
- `tools/environments/local.py` (3 sites kept as-is, suppressed with
`# windows-footgun: ok` — the pgid semantics psutil can't replicate,
and the calls are already Windows-guarded at the outer branch)
- `gateway/platforms/whatsapp.py`
### 4. `scripts/check-windows-footguns.py` (NEW, 500 lines)
Grep-based checker with 11 rules covering every Windows cross-platform
footgun we've hit so far:
1. `os.kill(pid, 0)` — the silent killer
2. `os.setsid` without guard
3. `os.killpg` (recommends psutil)
4. `os.getuid` / `os.geteuid` / `os.getgid`
5. `os.fork`
6. `signal.SIGKILL`
7. `signal.SIGHUP/SIGUSR1/SIGUSR2/SIGALRM/SIGCHLD/SIGPIPE/SIGQUIT`
8. `subprocess` shebang script invocation
9. `wmic` without `shutil.which` guard
10. Hardcoded `~/Desktop` (OneDrive trap)
11. `asyncio.add_signal_handler` without try/except
12. `open()` without `encoding=` on text mode
Features:
- Triple-quoted-docstring aware (won't flag prose inside docstrings)
- Trailing-comment aware (won't flag mentions in `# os.kill(pid, 0)` comments)
- Guard-hint aware (skips lines with `hasattr(os, ...)`,
`shutil.which(...)`, `if platform.system() != 'Windows'`, etc.)
- Inline suppression with `# windows-footgun: ok — <reason>`
- `--list` to print all rules with fixes
- `--all` / `--diff <ref>` / staged-files (default) modes
- Scans 380 files in under 2 seconds
### 5. CI integration
A GitHub Actions workflow that runs the checker on every PR and push is
staged at `/tmp/hermes-stash/windows-footguns.yml` — not included in this
commit because the GH token on the push machine lacks `workflow` scope.
A maintainer with `workflow` permissions should add it as
`.github/workflows/windows-footguns.yml` in a follow-up. Content:
```yaml
name: Windows footgun check
on:
push:
branches: [main]
pull_request:
branches: [main]
jobs:
check:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with: {python-version: "3.11"}
- run: python scripts/check-windows-footguns.py --all
```
### 6. CONTRIBUTING.md — "Cross-Platform Compatibility" expansion
Expanded from 5 to 16 rules, each with message, example, and fix.
Recommends psutil as the preferred API for PID / process-tree operations.
### 7. Baseline cleanup (91 → 0 findings)
- 14 `open()` sites → added `encoding='utf-8'` (internal logs/caches) or
`encoding='utf-8-sig'` (user-editable files that Notepad may BOM)
- 23 POSIX-only callsites in systemd helpers, pty_bridge, and plugin
tool subprocess management → annotated with
`# windows-footgun: ok — <reason>`
- 7 `os.killpg` sites → migrated to psutil (see §3 above)
## Verification
```
$ python scripts/check-windows-footguns.py --all
✓ No Windows footguns found (380 file(s) scanned).
$ python -c "from gateway.status import _pid_exists; import os
> print('self:', _pid_exists(os.getpid())); print('bogus:', _pid_exists(999999))"
self: True
bogus: False
```
Proof-of-repro that `os.kill(pid, 0)` was actually killing processes
before this fix — see commit `1cbe39914` and bpo-14484. This commit
removes the last hand-rolled ctypes path from the hot liveness-check
path and defers to the best-maintained cross-platform answer.
Closes the last Python-on-Windows UTF-8 exposure by making every
text-mode open() call explicit about its encoding.
Before: on Windows, bare open(path, 'r') defaults to the system
locale encoding (cp1252 on US-locale installs). That means reading
any config/yaml/markdown/json file with non-ASCII content either
crashes with UnicodeDecodeError or silently mis-decodes bytes.
After: all 89 affected call sites in production code now pass
encoding='utf-8' explicitly. Works identically on every platform
and every locale, no surprise behavior.
Mechanical sweep via:
ruff check --preview --extend-select PLW1514 --unsafe-fixes --fix --exclude 'tests,venv,.venv,node_modules,website,optional-skills, skills,tinker-atropos,plugins' .
All 89 fixes have the same shape: open(x) or open(x, mode) became
open(x, encoding='utf-8') or open(x, mode, encoding='utf-8'). Nothing
else changed. Every modified file still parses and the Windows/sandbox
test suite is still green (85 passed, 14 skipped, 0 failed across
tests/tools/test_code_execution_windows_env.py +
tests/tools/test_code_execution_modes.py + tests/tools/test_env_passthrough.py +
tests/test_hermes_bootstrap.py).
Scope notes:
- tests/ excluded: test fixtures can use locale encoding intentionally
(exercising edge cases). If we want to tighten tests later that's
a separate PR.
- plugins/ excluded: plugin-specific conventions may differ; plugin
authors own their code.
- optional-skills/ and skills/ excluded: skill scripts are user-authored
and we don't want to mass-edit them.
- website/ and tinker-atropos/ excluded: vendored / generated content.
46 files touched, 89 +/- lines (symmetric replacement). No behavior
change on POSIX or on Windows when the file is ASCII; bug fix on
Windows when the file contains non-ASCII.
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)
* 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>
Widen the platform-plugin surface so plugins can self-configure from env
vars and opt into cron home-channel delivery without editing core files.
Closes the scope gap that forced every new platform (Google Chat, Teams,
IRC, future) to either touch gateway/config.py, cron/scheduler.py, and
hermes_cli/config.py or live without env-only setup.
Changes:
- gateway/platform_registry.py: two new optional PlatformEntry fields.
- env_enablement_fn: () -> Optional[dict]. Called during
_apply_env_overrides BEFORE the adapter is constructed. Returned
dict fields are merged into PlatformConfig.extra; the special
'home_channel' key (if present) becomes a proper HomeChannel
dataclass on the PlatformConfig.
- cron_deliver_env_var: name of the *_HOME_CHANNEL env var. When set,
the plugin platform is a valid cron deliver= target and cron reads
the env var to resolve the default chat/room ID.
- gateway/config.py: the existing plugin-platform enable pass at the
bottom of _apply_env_overrides now calls env_enablement_fn and seeds
extras/home_channel. No effect on plugins that don't set the new
field.
- cron/scheduler.py: _is_known_delivery_platform and
_resolve_home_env_var fall through to the registry when the platform
isn't in the hardcoded built-in sets. New _iter_home_target_platforms
helper iterates built-ins + plugin platforms for the deliver=origin
fallback.
- gateway/run.py: _home_target_env_var now consults the new resolver so
plugin-defined home channels work for non-cron call sites too.
- hermes_cli/config.py: new _inject_platform_plugin_env_vars() sibling
of _inject_profile_env_vars(). Scans plugins/platforms/*/plugin.yaml
at import time and contributes entries to OPTIONAL_ENV_VARS so
'hermes config' UI discovers them. Supports bare-string and rich-dict
requires_env entries plus a new optional_env list for non-required
vars (home channels, allowlists).
All additions are strictly opt-in. Existing plugins (IRC, Teams,
image_gen, memory) see zero behavior change until they adopt the new
fields.
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).
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.
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).
Adds SearXNG as a free, self-hosted web search provider. SearXNG is a
privacy-respecting metasearch engine that requires no API key — just a
running instance and SEARXNG_URL pointing at it.
## What this adds
- `tools/web_providers/searxng.py` — `SearXNGSearchProvider` implementing
`WebSearchProvider` (search only; no extract capability)
- `_is_backend_available("searxng")` — gates on SEARXNG_URL
- `_get_backend()` — accepts "searxng" as a configured value; adds it to
auto-detect candidates (lower priority than paid services)
- `web_search_tool` — dispatches to SearXNG when it is the active backend
- `check_web_api_key()` — includes SearXNG in availability check
- `OPTIONAL_ENV_VARS["SEARXNG_URL"]` — registered with tools=["web_search"]
- `tools_config.py` — SearXNG appears in the `hermes tools` provider picker
- `nous_subscription.py` — `direct_searxng` detection, web_active / web_available
- `setup.py` — SEARXNG_URL listed in the missing-credential hint
- 23 tests covering: is_configured, happy-path search, score sorting, limit,
HTTP/request errors, _is_backend_available, _get_backend, check_web_api_key
## Config
```yaml
# Use SearXNG for search, any paid provider for extract
web:
search_backend: "searxng"
extract_backend: "firecrawl"
# Or: SearXNG as the sole backend (web_extract will use the next available)
web:
backend: "searxng"
```
SearXNG is search-only — it does not implement WebExtractProvider. Users
who only configure SEARXNG_URL get web_search available; web_extract falls
back to the next available extract provider (or is unavailable if none).
Closes#19198 (Phase 2 Task 4 — SearXNG provider)
Ref: #11562 (original SearXNG PR)
Introduce the foundation for independently selecting web search and
extract backends — enabling future combinations like SearXNG for
search + Firecrawl for extract.
Architecture:
- tools/web_providers/base.py: WebSearchProvider and WebExtractProvider
ABCs with normalized result contracts (mirrors CloudBrowserProvider)
- tools/web_tools.py: _get_search_backend() and _get_extract_backend()
read per-capability config keys, fall through to shared web.backend
- hermes_cli/config.py: web.search_backend and web.extract_backend in
DEFAULT_CONFIG (empty = inherit from web.backend)
Behavioral change:
- web_search_tool() now dispatches via _get_search_backend()
- web_extract_tool() now dispatches via _get_extract_backend()
- When per-capability keys are empty (default), behavior is identical
to before — _get_search_backend() falls through to _get_backend()
This is purely structural — no new backends are added. SearXNG and
other search-only/extract-only providers can now be added as simple
drop-in modules in follow-up PRs.
12 new tests, 49 existing tests pass with zero regressions.
Ref: #19198
* feat(skills/linear): add Documents support + Python helper script
The bundled Linear skill (PR #1230) covered issues, projects, teams, and
workflow states via curl. It had no coverage for Linear's Documents API,
so fetching an RFC/doc from a linear.app URL required hand-writing
GraphQL against an underdocumented schema.
Adds:
- Documents section in SKILL.md explaining slugId extraction from URLs,
the contentState (markdown) vs contentState (ProseMirror) split, and
four canonical curl examples (fetch by slugId, fetch by UUID, list
recent, title-search).
- scripts/linear_api.py — stdlib-only Python CLI wrapping the most
common operations (whoami, list-teams, list/get/search/create/update
issues, add-comment, update-status, list/get/search documents, raw
GraphQL passthrough). Zero deps, reads LINEAR_API_KEY from env.
Auth header quirk (personal key takes bare $LINEAR_API_KEY, no Bearer
prefix) is already documented in the skill.
Found during RFC review: the existing skill's lack of document support
forced falling back to the browser (which hit Linear's login wall).
Also fixes a schema gotcha — the Document field is `contentState`, not
`contentData` (which returns 400).
Tested end-to-end against the production API:
python3 linear_api.py whoami
python3 linear_api.py get-document 38359beef67c
Both return expected payloads.
* fix(skills/linear): point LINEAR_API_KEY setup to the correct page
The org-level Settings > API page (/settings/api) only shows OAuth apps
and workspace-member keys. Personal API keys live under Account,
Security, access (/settings/account/security). Update both the setup
link in config.py (shown during hermes setup) and the setup step in
SKILL.md so users land on the page that can create a personal key.
Replaces the per-directory shadow-repo design with a single shared shadow
git store at ~/.hermes/checkpoints/store/. Object DB is now deduplicated
across every working directory the agent has ever touched; a dozen
worktrees of the same project cost near-zero in additional disk.
Why
---
Pre-v2 design had three compounding problems that let ~/.hermes/checkpoints/
grow to multi-GB on active machines:
1. Each working directory got its own full shadow git repo — no object
dedup across projects or across worktrees of the same project.
2. _prune() was a documented no-op: max_snapshots only limited the
/rollback listing. Loose objects accumulated forever.
3. Defaults: enabled=True, auto_prune=False — users paid the disk cost
without ever asking for /rollback.
Field report on a single workstation: 847 MB across 47 shadow repos,
mostly redundant clones of the hermes-agent source tree.
Changes
-------
- tools/checkpoint_manager.py: full rewrite. Single bare store, per-project
refs (refs/hermes/<hash>), per-project indexes (store/indexes/<hash>),
per-project metadata (store/projects/<hash>.json with workdir +
created_at + last_touch). On first v2 init, any pre-v2 per-directory
shadow repos are auto-migrated into legacy-<timestamp>/ so the new
store starts clean. _prune() now actually rewrites the per-project ref
to the last max_snapshots commits and runs git gc --prune=now. New
_enforce_size_cap() drops oldest commits round-robin across projects
when the store exceeds max_total_size_mb. _drop_oversize_from_index()
filters any single file larger than max_file_size_mb out of the snapshot.
- hermes_cli/checkpoints.py: new 'hermes checkpoints' CLI
(status / list / prune / clear / clear-legacy) for managing the store
outside a session.
- hermes_cli/config.py: flipped defaults — enabled=False, max_snapshots=20,
auto_prune=True. Added max_total_size_mb=500, max_file_size_mb=10.
Tightened DEFAULT_EXCLUDES (added target/, *.so/*.dylib/*.dll,
*.mp4/*.mov, *.zip/*.tar.gz, .worktrees/, .mypy_cache/, etc.).
- run_agent.py / cli.py / gateway/run.py: thread the new kwargs through
AIAgent and the startup auto_prune hooks.
- Tests rewritten to match v2 storage while keeping backwards-compat
coverage for the pre-v2 prune path (per-directory shadow repos under
base/ are still swept correctly for anyone mid-migration).
- Docs updated: user-guide/checkpoints-and-rollback.md explains the
shared store, new defaults, migration, and the new CLI;
reference/cli-commands.md documents 'hermes checkpoints'.
E2E validated
-------------
- Legacy migration: pre-v2 shadow repos auto-archived into legacy-<ts>/.
- Object dedup: two projects with an identical shared.py blob resolve to
7 total objects in the store (v1 would have stored the blob twice).
- max_snapshots=3 actually enforced: after 6 commits, list shows 3.
- Orphan prune: deleting a project's workdir + 'hermes checkpoints prune
--retention-days 0' removes its ref, index, and metadata; GC reclaims
the objects.
- max_file_size_mb=1 excludes a 2 MB weights.bin while keeping the
tracked source code files.
- hermes checkpoints {status,prune,clear,clear-legacy} all work from the
CLI without an agent running.
Breaking / migration
--------------------
No in-place data migration — legacy per-directory shadow repos are moved
into legacy-<timestamp>/ on first run. Old /rollback history is still
accessible by inspecting the archive with git; run
'hermes checkpoints clear-legacy' to reclaim the space when ready. Users
relying on /rollback must now set checkpoints.enabled=true (or pass
--checkpoints) explicitly.
Add Lightpanda as an optional browser engine for local mode.
Lightpanda is a headless browser built from scratch in Zig -- faster
navigation than Chrome with significantly less memory.
One config line to enable:
browser:
engine: lightpanda
New functions in browser_tool.py:
- _get_browser_engine() -- config/env reader with validation + caching
- _should_inject_engine() -- only inject in local non-cloud mode
- _needs_lightpanda_fallback() -- detect empty/failed LP results
- _chrome_fallback_screenshot() -- temporary Chrome session for screenshots
- Engine injection in _run_browser_command (--engine flag)
- browser_vision pre-routes screenshots to Chrome when engine=lightpanda
Config:
- browser.engine in DEFAULT_CONFIG (auto/lightpanda/chrome)
- AGENT_BROWSER_ENGINE in OPTIONAL_ENV_VARS
- /browser status shows engine info in local mode
Rebased from PR #7144 onto current main. All existing code preserved --
pure additions only (+520/-2).
25 new tests + 81 total browser tests pass (0 failures).
- hermes_cli/config.py: add tr to supported languages comment
- locales/en.yaml: add tr to locale file list comment
- tests/agent/test_i18n.py: add Turkish alias tests + explicit lang test
- website/docs/user-guide/configuration.md: add tr to supported values
Introduces providers/ package — single source of truth for every
inference provider. Adding a simple api-key provider now requires one
providers/<name>.py file with zero edits anywhere else.
What this PR ships:
- providers/ package (ProviderProfile ABC + 33 profiles across 4 api_modes)
- ProviderProfile declarative fields: name, api_mode, aliases, display_name,
env_vars, base_url, models_url, auth_type, fallback_models, hostname,
default_headers, fixed_temperature, default_max_tokens, default_aux_model
- 4 overridable hooks: prepare_messages, build_extra_body,
build_api_kwargs_extras, fetch_models
- chat_completions.build_kwargs: profile path via _build_kwargs_from_profile,
legacy flag path retained for lmstudio/tencent-tokenhub (which have
session-aware reasoning probing that doesn't map cleanly to hooks yet)
- run_agent.py: profile path for all registered providers; legacy path
variable scoping fixed (all flags defined before branching)
- Auto-wires: auth.PROVIDER_REGISTRY, models.CANONICAL_PROVIDERS,
doctor health checks, config.OPTIONAL_ENV_VARS, model_metadata._URL_TO_PROVIDER
- GeminiProfile: thinking_config translation (native + openai-compat nested)
- New tests/providers/ (79 tests covering profile declarations, transport
parity, hook overrides, e2e kwargs assembly)
Deltas vs original PR (salvaged onto current main):
- Added profiles: alibaba-coding-plan, azure-foundry, minimax-oauth
(were added to main since original PR)
- Skipped profiles: lmstudio, tencent-tokenhub stay on legacy path (their
reasoning_effort probing has no clean hook equivalent yet)
- Removed lmstudio alias from custom profile (it's a separate provider now)
- Skipped openrouter/custom from PROVIDER_REGISTRY auto-extension
(resolve_provider special-cases them; adding breaks runtime resolution)
- runtime_provider: profile.api_mode only as fallback when URL detection
finds nothing (was breaking minimax /v1 override)
- Preserved main's legacy-path improvements: deepseek reasoning_content
preserve, gemini Gemma skip, OpenRouter response caching, Anthropic 1M
beta recovery, etc.
- Kept agent/copilot_acp_client.py in place (rejected PR's relocation —
main has 7 fixes landed since; relocation would revert them)
- _API_KEY_PROVIDER_AUX_MODELS alias kept for backward compat with existing
test imports
Co-authored-by: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Closes#14418
* revert(gateway): remove stale-code self-check and auto-restart
Removes the _detect_stale_code / _trigger_stale_code_restart mechanism
introduced in #17648 and iterated in #19740. On every incoming message
the gateway compared the boot-time git HEAD SHA to the current SHA on
disk, and if they differed it would reply with
Gateway code was updated in the background --
restarting this gateway so your next message runs
on the new code. Please retry in a moment.
and then kick off a graceful restart. This is unwanted behaviour:
users who run a long-lived gateway and do their own ad-hoc git
operations on the checkout end up with their chat interrupted and
the current message dropped every time HEAD moves, with no way to
opt out.
If an operator really needs the old protection against stale
sys.modules after "hermes update", the SIGKILL-survivor sweep in
hermes update (hermes_cli/main.py, also tagged #17648) already
handles the supervisor-respawn case on its own.
Removed:
gateway/run.py:
- _STALE_CODE_SENTINELS, _GIT_SHA_CACHE_TTL_SECS
- _read_git_head_sha(), _compute_repo_mtime() module helpers
- class-level _boot_wall_time / _boot_repo_mtime / _boot_git_sha /
_stale_code_restart_triggered defaults
- __init__ boot-snapshot block (_boot_*, _cached_current_sha*,
_repo_root_for_staleness, _stale_code_notified)
- _current_git_sha_cached(), _detect_stale_code(),
_trigger_stale_code_restart() methods
- stale-code check + user-facing restart notice at the top of
_handle_message()
tests/gateway/test_stale_code_self_check.py (deleted, 412 lines)
No new logic added. Zero remaining references to any removed
symbol. Gateway test suite passes the same 4589 tests it passed
before; the 3 pre-existing unrelated failures (discord free-channel,
feishu bot admission, teams typing) are unchanged by this commit.
* feat(i18n): add display.language for static message translation (zh/ja/de/es)
Adds a thin-slice i18n layer covering the highest-impact static user-facing
messages: the CLI dangerous-command approval prompt and a handful of gateway
slash-command replies (restart-drain, goal cleared, approval expired, config
read/save errors).
Out of scope (stays English): agent responses, log lines, tool outputs,
slash-command descriptions, error tracebacks.
Infrastructure:
- agent/i18n.py: catalog loader, t() helper, language resolution
(HERMES_LANGUAGE env var > display.language config > en)
- locales/{en,zh,ja,de,es}.yaml: ~19 translated strings per language
- display.language in DEFAULT_CONFIG (hermes_cli/config.py)
Tests:
- tests/agent/test_i18n.py: 21 tests covering catalog parity, placeholder
parity across locales, fallback behavior, env-var override, alias
normalization, missing-key graceful degradation.
Docs:
- website/docs/user-guide/configuration.md: display.language entry plus a
short section explaining scope so users don't expect agent responses to
translate via this knob.
`updates.backup_keep: 0` (or any negative value) wiped the freshly-
created pre-update zip:
_prune_pre_update_backups(backup_dir, keep=0):
backups = sorted(..., reverse=True) # newest first, includes
# the zip we just wrote
for p in backups[0:]: # = all of them
p.unlink()
The wrapper in `main.py` then printed `Saved: <path>` for a file that
no longer existed (the size lookup is wrapped in `try/except OSError`
which silently degrades to "0 B"), leaving operators believing they had
a recovery point when they had none.
This is a real footgun because some config systems treat 0 as "keep
unlimited"; here it does the opposite — every backup is destroyed
right after creation.
Fix: clamp `keep` to a minimum of 1 inside `_prune_pre_update_backups`
since that helper is only invoked immediately after a fresh backup
is written. Operators who genuinely want no backups should set
`updates.pre_update_backup: false` (which gates creation entirely)
rather than relying on `backup_keep: 0`.
Also extends the `backup_keep` config docstring to spell out the floor
and point at `pre_update_backup: false` as the off-switch.
## Tests
Three regression tests added in `TestPreUpdateBackup`:
- `test_keep_zero_does_not_delete_freshly_created_backup` —
asserts the file persists after `keep=0`
- `test_keep_negative_does_not_delete_freshly_created_backup` —
same for negative values
- `test_keep_zero_still_prunes_older_backups` — proves the floor
only protects the new backup; older ones are still rotated out
Verified the new tests fail on origin/main (without the floor) and
pass with it; full `tests/hermes_cli/test_backup.py` suite green
(84 tests).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The old CWD heuristic was fooled by:
1. TERMINAL_CWD persisted to .env by `hermes config set terminal.cwd`
2. Inherited TERMINAL_CWD from parent hermes processes
3. Only resolved when config had a placeholder value (not explicit paths)
Fix:
- load_cli_config() unconditionally uses os.getcwd() for local backend
- TERMINAL_CWD always force-exported in CLI mode (overrides stale values)
- Gateway sets _HERMES_GATEWAY=1 marker so lazy cli.py imports don't clobber
- Remove terminal.cwd from config-set .env sync map (prevents re-poisoning)
- Clarify setup wizard label as 'Gateway working directory'
Closes#19214
Enable OpenRouter's response caching feature (beta) via X-OpenRouter-Cache
headers. When enabled, identical API requests return cached responses for
free (zero billing), reducing both latency and cost.
Configuration via config.yaml:
openrouter:
response_cache: true # default: on
response_cache_ttl: 300 # 1-86400 seconds
Changes:
- Add openrouter config section to DEFAULT_CONFIG (response_cache + TTL)
- Add build_or_headers() in auxiliary_client.py that builds attribution
headers plus optional cache headers based on config
- Replace inline _OR_HEADERS dicts with build_or_headers() at all 5 sites:
run_agent.py __init__, _apply_client_headers_for_base_url(), and
auxiliary_client.py _try_openrouter() + _to_async_client()
- Add _check_openrouter_cache_status() method to AIAgent that reads
X-OpenRouter-Cache-Status from streaming response headers and logs
HIT/MISS status
- Document in cli-config.yaml.example
- Add 28 tests (22 unit + 6 integration)
Ref: https://openrouter.ai/docs/guides/features/response-caching
Point users to xAI's custom voices feature — clone your voice in the
console, paste the voice_id into tts.xai.voice_id. No code changes
needed; the existing TTS pipeline already handles arbitrary voice IDs.
- config.py: link to xAI custom voices docs in voice_id comment
- setup.py: prompt accepts custom voice IDs during xAI TTS setup
- tts.md: short section linking to xAI console and docs
* fix(gateway): config.yaml wins over .env for agent/display/timezone settings
Regression from the silent config→env bridge. The bridge at module import
time is correct for max_turns (unconditional overwrite), but every other
agent.*, display.*, timezone, and security bridge key was guarded by
'if X not in os.environ' — so a stale .env entry from an old 'hermes setup'
run would shadow the user's current config.yaml indefinitely.
Symptom: agent.max_turns: 500 in config.yaml, HERMES_MAX_ITERATIONS=60
in .env from an old setup, and the gateway silently capped at 60
iterations per turn. Gateway logs confirmed api_calls never exceeded 60.
Three changes:
1. gateway/run.py: drop the 'not in os.environ' guards for all agent.*,
display.*, timezone, and security.* bridge keys. config.yaml is now
authoritative for these settings — same semantics already in place
for max_turns, terminal.*, and auxiliary.*. Also surface the bridge
failure (previously 'except Exception: pass') to stderr so operators
see bridge errors instead of silently falling back to .env.
2. gateway/run.py: INFO-log the resolved max_iterations at gateway
start so operators can verify the config→env bridge did the right
thing instead of chasing a phantom budget ceiling.
3. hermes_cli/setup.py: stop writing HERMES_MAX_ITERATIONS to .env in
the setup wizard. config.yaml is the single source of truth. Also
clean up any stale .env entry left behind by pre-fix setups.
Regression tests in tests/gateway/test_config_env_bridge_authority.py
guard each config→env key against the 'stale .env shadows config' bug.
* fix(gateway): shutdown + restart hygiene (drain timeout, false-fatal, success log)
Three issues observed in production gateway.log during a rapid restart
chain on 2026-05-02, all fixed here.
1. _send_restart_notification logged unconditional success
adapter.send() catches provider errors (e.g. Telegram 'Chat not found')
and returns SendResult(success=False); it never raises. The caller
ignored the return value and always logged 'Sent restart notification
to <chat>' at INFO, producing a misleading success line directly
below the 'Failed to send Telegram message' traceback on every boot.
Now inspects result.success and logs WARNING with the error otherwise.
2. WhatsApp bridge SIGTERM on shutdown classified as fatal error
_check_managed_bridge_exit() saw the bridge's returncode -15 (our own
SIGTERM from disconnect()) and fired the full fatal-error path,
producing 'ERROR ... WhatsApp bridge process exited unexpectedly' plus
'Fatal whatsapp adapter error (whatsapp_bridge_exited)' on every
planned shutdown, immediately before the normal '✓ whatsapp
disconnected'. Adds a _shutting_down flag that disconnect() sets
before the terminate, and _check_managed_bridge_exit() returns None
for returncode in {0, -2, -15} while shutting down. OOM-kill (137)
and other non-signal exits still hit the fatal path.
3. restart_drain_timeout default 60s → 180s
On 2026-05-02 01:43:27 a user /restart fired while three agents were
mid-API-call (82s, 112s, 154s into their turns). The 60s drain budget
expired and all three were force-interrupted. 180s covers realistic
in-flight agent turns; users on very-long-reasoning models can still
raise it further via agent.restart_drain_timeout in config.yaml.
Existing explicit user values are preserved by deep-merge.
Tests
- tests/gateway/test_restart_notification.py: two new tests assert INFO
is only logged on SendResult(success=True) and WARNING with the error
string is logged on SendResult(success=False).
- tests/gateway/test_whatsapp_connect.py: parametrized test for
returncode in {0, -2, -15} proves shutdown-time exits are suppressed;
separate test proves returncode 137 (SIGKILL/OOM) still surfaces as
fatal even when _shutting_down is set.
- _check_managed_bridge_exit() reads _shutting_down via getattr-with-
default so existing _make_adapter() test helpers that bypass __init__
(pitfall #17 in AGENTS.md) keep working unmodified.
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes#18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
Add a standing-goal slash command that keeps Hermes working toward a
user-stated objective across turns until it is achieved, paused, or
the turn budget runs out. Our take on the Ralph loop — cf. Codex CLI
0.128.0's /goal.
After each turn, a lightweight auxiliary-model judge call asks 'is
this goal satisfied by the assistant's last response?'. If not, and
we're under the turn budget (default 20), Hermes feeds a continuation
prompt back into the same session as a normal user message. Any real
user message preempts the continuation loop automatically.
Judge failures fail OPEN (continue) so a flaky judge never wedges
progress — the turn budget is the real backstop.
### Commands
- `/goal <text>` — set a standing goal (kicks off the first turn)
- `/goal` or `/goal status` — show current state
- `/goal pause` — pause the continuation loop
- `/goal resume` — resume (resets turn counter)
- `/goal clear` — drop the goal
Works on both CLI and gateway platforms via the central CommandDef
registry.
### Design invariants preserved
- **Prompt cache**: continuation prompts are regular user-role
messages appended to history. No system-prompt mutation, no toolset
swap.
- **Role alternation**: continuation is a user turn, never injected
mid-tool-loop.
- **Session persistence**: goal state lives in SessionDB.state_meta
keyed by `goal:<session_id>`, so `/resume` picks it up.
- **Mid-run safety**: on the gateway, `/goal status|pause|clear` are
allowed mid-run (control-plane only); setting a new goal requires
`/stop` first so we don't race a second continuation prompt against
the current turn.
### Files
- `hermes_cli/goals.py` (new, 380 lines) — GoalManager + judge + state
- `hermes_cli/commands.py` — CommandDef entry
- `hermes_cli/config.py` — `goals.max_turns` default
- `hermes_cli/web_server.py` — dashboard category merge
- `cli.py` — /goal handler + post-turn continuation hook in
process_loop
- `gateway/run.py` — /goal handler + post-turn continuation hook
wrapping _handle_message_with_agent
- `tests/hermes_cli/test_goals.py` (new, 26 tests) — judge parsing,
fail-open semantics, lifecycle, persistence, budget exhaustion
- `website/docs/reference/slash-commands.md` — docs entry
Adds opt-in auto-deletion for slash-command reply messages like
"New session started!", "Restarting gateway…", "Stopped.", and
YOLO toggles. After the TTL elapses the gateway calls the adapter's
delete_message; on platforms without a delete API (everything except
Telegram today) the TTL is silently ignored and the message stays.
Requested on Twitter by @charlesmcdowell — tool-call bubbles are useful
real-time, but system notices clutter the thread once the agent finishes.
Implementation:
- EphemeralReply(str) sentinel in gateway/platforms/base.py. Subclasses
str so existing 'X' in response / response.startswith(...) checks in
tests and call sites keep working unchanged; isinstance() still
distinguishes it for the send path.
- _process_message_background and both busy-session bypass paths
(in base.py) call _unwrap_ephemeral() on the handler return, send
the unwrapped text, and schedule a detached delete task when the
TTL > 0 AND the adapter class overrides delete_message.
- display.ephemeral_system_ttl (default 0 = disabled) in DEFAULT_CONFIG.
Handler can pass ttl_seconds explicitly to override.
- Wrapped the highest-noise return sites: /new, /reset, /stop,
/yolo on/off, /restart success + "already in progress". Draining
notices and /help output left as plain strings — those are
informational and users want to read them.
Backward-compat: default TTL 0 → no scheduling, no behavior change
for existing users. Platforms without delete_message silently no-op.
`hermes update` ran the config migration (11 → 17) successfully then
crashed at `agent/skill_utils.py:340` during the post-migration
skill-config prompt. User @FlockonUS reported this on Twitter.
Root cause: `get_missing_skill_config_vars` in hermes_cli/config.py
only guarded the import of `discover_all_skill_config_vars`, not the
call. Any runtime exception inside the skill scan (malformed SKILL.md,
unreadable external skill dir, etc.) propagated up through
`migrate_config` and aborted `hermes update` after the version bump.
Wrap the call in try/except so skill-config prompting — which is a
post-migration nicety — can never block the migration itself.
Refactor tool resolution logic in model_tools.py to ensure that
disabled_toolsets are always subtracted at the end, preventing
composite toolsets (e.g. 'browser') from implicitly enabling tools
that should be hidden.
- Added 'disabled_toolsets' to DEFAULT_CONFIG in hermes_cli/config.py
- Updated HermesCLI in cli.py to load and propagate disabled toolsets to AIAgent
- Implemented robust two-phase resolution (additive then subtractive) in model_tools.py
Three fixes bundled for curator reliability on existing installs and
broken/partial installs:
1. run_agent.py: defer `import fire` into the __main__ block. `fire` is
only used by `fire.Fire(main)` when running run_agent.py directly as
a CLI — it is NOT needed for library usage. Importing it at module
top made `from run_agent import AIAgent` from a daemon thread (e.g.
the curator's forked review agent) crash with ModuleNotFoundError
on broken/partial installs where `fire` isn't present.
2. hermes_cli/config.py: add version 22 → 23 migration that writes the
`curator` + `auxiliary.curator` sections to config.yaml with their
defaults, only filling keys the user hasn't overridden. Existing
configs from before PR #16049 / the April 2026 `auxiliary.curator`
unification had neither section on disk, so users couldn't see or
edit the settings in their config.yaml (runtime deep-merge papered
over it at read time, but the file never reflected reality).
3. hermes_cli/config.py: `ensure_hermes_home()` now pre-creates
`~/.hermes/logs/curator/` alongside cron/sessions/logs/memories on
every CLI launch. Managed-mode (NixOS) variant mkdir's it
defensively after the activation-script existence checks, since the
activation script may not know about this subpath.
4. agent/curator.py: `_reports_root()` mkdir's the dir at call time as
belt-and-suspenders for entry paths that bypass both
ensure_hermes_home() and the v23 migration (gateway-only installs,
bare library use).
E2E validated in isolated HERMES_HOME: fresh install gets full defaults
seeded; partial-override config keeps user's `enabled: false` and
custom `interval_hours` while filling the missing keys; re-running the
migration is a no-op.
