User incident (Slack, 2026-05-13): user walked away mid-conversation,
agent requested approval to run `rm -rf .git`, the prompt timed out
after the gateway_timeout (default 300s), and the agent removed the
.git folder on its own. Corroborated by an independent report from a
Telegram user.
The underlying code path was correct — `check_all_command_guards`
returns `approved=False` with a BLOCKED message on both timeout and
explicit deny, and `terminal_tool` surfaces that as `status=blocked`
to the agent. The bug is at the model-interface layer: the message
"BLOCKED: Command timed out. Do NOT retry this command." reads to
some models as "try a different command achieving the same outcome."
This commit changes only the model-facing message + the structured
return shape:
- Timeout message now explicitly names the three evasion paths the
agent must avoid: retry, rephrase, AND achieve the same outcome
via a different command. Ends with "Silence is not consent."
- Explicit deny gets the same shape minus the silence-is-not-consent
line (it WAS an explicit deny, not silence).
- New structured fields on the return dict: `outcome` ("timeout"
or "denied") and `user_consent` (always False on this branch)
so plugins, hooks, and audit pipelines don't have to string-parse
the message to distinguish the two cases.
The mechanism that should already have prevented the original incident
— timeout treated as deny, BLOCKED result, post hook fires with
`choice="timeout"` — is unchanged. This commit hardens only the
agent's reading of the result.
Tests:
- test_timeout_returns_approved_false_with_no_consent — pins the
return shape on the Slack-shaped notify_cb-registered path
- test_timeout_message_is_emphatic_against_retry_and_rephrase —
pins the exact phrases the message must contain
- test_explicit_deny_carries_same_no_consent_shape — same contract
on explicit /deny
- test_timeout_emits_post_hook_with_timeout_outcome — pins the
post_approval_response hook payload so audit plugins can act
329 approval tests passing (4 new + 325 existing).
Fixes#24912
Reproduction (production, 2026-05-14): two concurrent sessions on the
same agent. Session A patches MEMORY.md directly via the patch tool,
appending ~8KB of structured content (Vendor Master, Standing Orders,
Pin Board) — none of it through the memory tool, so no § delimiters.
Session B starts later with stale in-memory state (1 entry, ~331
chars). Session B calls memory(action=replace) on its one known
entry. The tool's _read_file parses A's content as a single 8KB
'entry' (no § splits), then replace truncates that entry to B's new
333-byte content. ~8KB of structured content silently destroyed.
The atomic-rename write path is fine in isolation. The bug is the
implicit contract: the tool assumes MEMORY.md is exclusively a
§-delimited list of small entries it wrote, but the v0.13 install
runbook itself uses 'cat >> MEMORY.md' for onboarding, the patch tool
edits the file directly, and operators do too.
Fix: a drift guard in MemoryStore._detect_external_drift that fires
on either signal:
1. Re-parse + re-serialize doesn't produce identical bytes
(catches oddly-encoded delimiters / partial writes).
2. Any single parsed entry exceeds the store's whole-file char
limit. The tool budgets the ENTIRE store against that limit
(2200 chars for memory, 1375 for user), so no tool-written
entry can legitimately be larger. An entry bigger than the
store limit means an external writer dropped free-form content
into what the tool will treat as one entry.
When drift fires, _reload_target writes a .bak.<ts> snapshot of the
on-disk file, then add/replace/remove refuse to flush. The original
file stays untouched. The error dict surfaces the .bak path AND a
remediation string ('integrate missing entries via memory(add=...)
one at a time, then rewrite the file clean') so the model can act on
it without escalating to the operator.
Tests:
- test_replace_refuses_on_drift, test_add_refuses_on_drift,
test_remove_refuses_on_drift — all three mutators refuse
- test_clean_file_does_not_trigger_drift — false-positive check
- test_error_message_points_at_remediation — error string shape
- test_drift_guard_also_protects_user_target — USER.md too
- test_drift_backup_filename_is_unique_per_invocation — bak.<ts>
naming pin
144 memory tests passing (was 137; +7).
Fixes#26045
Eleven new tests pinning the #29344 fix. Layout mirrors the existing
"Fix D" entitlement section so the bad-credentials disambiguator
sits alongside the entitlement-block tests it complements.
Classifier-level coverage:
* ``test_is_entitlement_failure_false_for_bad_credentials_wke_suffix``
— verbatim shape from the reporter's wire capture
(``{code: 'caller does not have permission', error: 'OAuth2 access
token could not be validated. [WKE=unauthenticated:bad-credentials]'}``)
↦ classifier must return False so the refresh path runs.
* ``test_is_entitlement_failure_false_for_wke_suffix_in_normalized_shape``
— same body after ``_extract_api_error_context`` has rewritten it
to ``{reason, message}``. The disambiguator must fire in BOTH
shapes; without this guard the production call site at
``_recover_with_credential_pool`` (which goes through the
normalised extractor) would still misclassify.
* ``test_is_entitlement_failure_false_for_any_wke_unauthenticated_variant``
— parametrised forward-compat: ``bad-credentials``,
``expired-token``, ``revoked``, ``some-future-reason``. xAI
documents the prefix as stable, the suffix after the colon as a
reason code that can grow; every variant under
``unauthenticated:`` must route to refresh.
* ``test_is_entitlement_failure_false_via_oauth2_validation_phrase_alone``
— belt-and-braces guard: if a future API revision drops the WKE
suffix but keeps "OAuth2 access token could not be validated", we
still classify correctly.
* ``test_is_entitlement_failure_wke_signal_overrides_entitlement_keywords``
— defensive: if a body ever carries BOTH the WKE suffix and
entitlement language, the WKE signal wins. Auth is recoverable;
entitlement isn't, and a refreshed token will resurface the
entitlement message on the next request.
* ``test_is_entitlement_failure_case_insensitive_wke_match`` —
pins that the classifier lowercases the haystack so a future xAI
build that uppercases the prefix doesn't reintroduce the bug.
Recovery-path coverage (end-to-end through
``_recover_with_credential_pool``):
* ``test_recover_with_credential_pool_refreshes_on_xai_bad_credentials_403``
— the headline test the reporter requested: a bad-credentials 403
with the exact wire body must call ``try_refresh_current()``
exactly once and ``_swap_credential`` once. Pre-fix this returned
``(False, _)`` because the entitlement classifier over-matched and
short-circuited the refresh path.
* ``test_recover_with_credential_pool_still_blocks_real_entitlement``
— companion regression guard for #26847: a pure unsubscribed-
account body (no WKE suffix, no OAuth2-validation phrase) must
still surface as entitlement and skip refresh. The new
disambiguator must not weaken the original loop-protection it
was added to preserve.
The scaffolding reuses ``_make_codex_agent``, ``_FakePool``, and the
existing ``MagicMock`` patterns from the surrounding tests so the
new section reads as a natural extension of "Fix D" rather than a
separate test file.
Closes#30045. Based on @qike-ms's PR #30141.
Telegram status callbacks (lifecycle, compression, context-pressure)
used to append a fresh bubble on every emit. Now adapter tracks
{(chat_id, status_key) -> message_id}; first call sends, subsequent
calls edit. Failed edits drop the cache entry and fall through to a
fresh send.
- gateway/platforms/telegram.py: send_or_update_status() (+34 LOC)
- gateway/run.py: route _status_callback_sync through it when the
adapter supports it; plain adapter.send() otherwise (+15 LOC)
- 5 tests covering first send / edit-in-place / edit-failure fallback
/ distinct key & chat isolation
PR 2362cc468 ("fix(gateway): enforce env variable template expansion
on runtime config loaders") refactored `_load_service_tier` to read
config via the new `_load_gateway_runtime_config` wrapper instead of
opening `_hermes_home/config.yaml` directly. The
`test_run_agent_passes_priority_processing_to_gateway_agent` test still
only stubbed `_load_gateway_config` (the inner loader), so the runtime
wrapper saw an empty config and `_load_service_tier` returned None,
breaking the test:
FAILED tests/gateway/test_fast_command.py::test_run_agent_passes_priority_processing_to_gateway_agent
- AssertionError: assert None == 'priority'
Fix: also stub `_load_gateway_runtime_config` to return the expected
`agent.service_tier=fast` config, so the test once again drives the
priority routing path it was written to verify.
Confirmed reproducing on current main before the patch and passing
after.
Follow-up to @sprmn24's verdict-logic fix. The previous block-message
ended in 'Use --force to override' regardless of verdict — but as of
the --force fix above, dangerous community/trusted skills can't be
overridden by --force at all. The misleading hint sends users in a
loop. Replace it with a specific message that tells them what the
documented behavior actually is.
Adds two regression tests covering the dangerous-verdict message
shape and one that pins the existing --force hint for non-dangerous
blocks.
`_deliver_kanban_artifacts` routes candidates through
`BasePlatformAdapter.filter_local_delivery_paths` (added in 41d2c758c),
which rejects paths outside `MEDIA_DELIVERY_SAFE_ROOTS`. The two
artifact-delivery tests create fixtures under `tmp_path`, which lives
outside the cache roots — so under CI's hermetic HOME the filter
silently dropped both fake files and the assertions on
`images_uploaded` / `documents_uploaded` failed.
Fix: monkeypatch `HERMES_MEDIA_ALLOW_DIRS=str(tmp_path)` in both tests
so the safety filter accepts the fixtures. Production behaviour
unchanged; test-side fix only.
CI fail repro on origin/main: test (6) shard, both
test_notifier_uploads_artifacts_on_completion and
test_notifier_artifact_delivery_skips_missing_files.
Ten regressions across both prongs of the #29507 fix, organised so each
test names exactly which way the bug could come back:
Prong 1 — ``force_close_tcp_sockets``:
* ``shutdown_only_no_close`` is the smoking-gun assertion. If a future
refactor adds back ``sock.close()`` to this helper, the FD-recycling
race that wrote TLS bytes on top of ``kanban.db`` is back, and this
trips.
* ``uses_shut_rdwr`` pins that both halves are shut down (a half-close
wouldn't unblock a worker stuck in ``recv``).
* ``swallows_oserror_on_shutdown`` covers the already-shutdown case.
* ``handles_multiple_pool_entries`` walks all pool connections.
Prong 2 — thread-aware ``_close_request_client_once``:
* ``stranger_thread_aborts_only_no_close`` simulates the asyncio_0 →
Thread-1616 interrupt path: stranger drives abort, holder stays
populated for the worker's eventual finally.
* ``owner_thread_pops_and_full_close`` is the worker-thread path: pops
+ full close.
* ``stranger_then_owner_close_sequence_runs_full_close_exactly_once``
replays the reporter's exact timeline at object level: abort runs
once, full close runs once, holder ends empty.
Agent surface:
* ``_abort_request_openai_client_does_not_call_client_close`` pins
that the new entrypoint shuts sockets and emits the
``deferred_close=stranger_thread`` marker but never calls
``client.close()``.
* ``_abort_request_openai_client_null_client_is_noop`` defensive.
End-to-end:
* ``fd_recycle_window_closed_by_shutdown_only`` reproduces the race
at object level — runs the abort path from a stranger thread and
asserts that no ``close()`` ever fires, so the kernel can never
recycle the FD under the owner's still-active reference.
The helper used to call ``socket.shutdown(SHUT_RDWR)`` followed by
``socket.close()`` to drop CLOSE-WAIT entries immediately. On its own
``shutdown()`` is safe from any thread — it only sends FIN and breaks
pending ``recv``/``send`` — but ``close()`` releases the FD integer to
the kernel. When the helper runs on a stranger thread (the interrupt
loop, the stale-call detector) the FD release races the owning httpx
worker thread that still has the same integer cached inside the SSL
BIO. The kernel then recycles that integer to the next ``open()`` call
— in production, kanban dispatcher's ``kanban.db`` — and the worker's
delayed TLS flush writes a 24-byte TLS application-data record on top
of the SQLite header.
Restrict the helper to ``shutdown(SHUT_RDWR)`` only. The owning httpx
worker's own unwind will close the underlying socket via the same
Python ``socket.socket`` object, which atomically swaps ``_fd`` to -1
before issuing ``close(2)`` — no FD-aliasing window.
The log field ``tcp_force_closed=N`` is kept (now counts shutdowns) so
existing dashboards / log parsers keep working.
Add original_name parameter to _download_and_cache, preferring the
attachment metadata filename over the CDN URL path basename. Previously
files were cached with meaningless QQ CDN hash names (e.g.
qqdownload_...oadftnv5), causing ugly filenames when sent back to users.
Aligns with qqbot-agent-sdk's AttachmentDownloader.download_document.
1. Handle op 7 (Server Reconnect): close WS to trigger reconnect loop
while preserving session for Resume
2. Handle op 9 (Invalid Session): check d value to determine if session
is resumable; clear session only when not resumable
3. Remove 4009 from session-clearing set (connection timeout is resumable)
4. Expand fatal close codes: 4001/4002/4010-4014 now stop reconnect
immediately instead of retrying uselessly
5. Add unit tests
1. Add INTERACTION intent bit (1<<26) to _send_identify, fixing approval
button clicks not being received (INTERACTION_CREATE events were never
dispatched by the gateway)
2. Include local cached path in video/file attachment descriptions so the
LLM can reference files for re-sending to users
3. Add unit tests (TestIdentifyIntents, TestProcessAttachmentsPathExposure)
PR #41d2c758c ("Fix unsafe gateway media path delivery") tightened
`validate_media_delivery_path` so that artifacts emitted by the agent
must live inside `MEDIA_DELIVERY_SAFE_ROOTS` (Hermes-managed cache
dirs) or an operator-allowlisted root via `HERMES_MEDIA_ALLOW_DIRS`.
Two kanban-notifier tests put their PDFs and PNGs under pytest's
`tmp_path`, which is correctly rejected by the new validator. They
started failing on main as soon as that PR landed:
FAILED tests/hermes_cli/test_kanban_notify.py::test_notifier_uploads_artifacts_on_completion
FAILED tests/hermes_cli/test_kanban_notify.py::test_notifier_artifact_delivery_skips_missing_files
Symptom in logs: "Skipping unsafe local file path outside allowed
roots". The validator is doing exactly what it should — the tests were
relying on the looser pre-fix behaviour.
Fix: add `HERMES_MEDIA_ALLOW_DIRS=tmp_path` to the `kanban_home`
fixture so artifacts under `tmp_path` are recognised as safe. This is
the same allowlist mechanism the operator-facing env var documents.
The Kimi K2 branch added in the prior commit only emitted extra_body.thinking
and dropped reasoning_effort entirely. KimiProfile (api.moonshot.ai/v1) sends
both fields, and OpenCode Go proxies to the same Moonshot backend. Mirror that
shape on the Go path so /reasoning effort actually reaches Kimi.
- low/medium/high pass through verbatim
- xhigh/max clamp to high (Moonshot's max supported value)
- minimal / unknown effort → omit reasoning_effort, keep thinking on
- disabled / no config → unchanged
- DeepSeek branch unchanged
The two ACP slash-command tests that exercise `provider:model` routing
(`test_set_session_model_accepts_provider_prefixed_choice` and
`test_model_switch_uses_requested_provider`) relied on the live
`hermes_cli.models._KNOWN_PROVIDER_NAMES` / `_PROVIDER_ALIASES` module
state to parse `anthropic:claude-sonnet-4-6` into
`("anthropic", "claude-sonnet-4-6")`. If any earlier test in the same
xdist worker registers a custom provider that shadows `anthropic` or
otherwise mutates those globals, the parser falls into the
`detect_provider_for_model` branch and resolves to `custom` instead.
Observed once in CI on run 26326728502 / job 77505732299 as
`AssertionError: assert 'custom' == 'anthropic'` — could not reproduce
locally under per-file isolation, so the failing in-file order was
specific to a particular xdist scheduling.
Monkeypatching `parse_model_input` + `detect_provider_for_model` for
both tests removes the global-catalog dependency, so the tests now only
exercise what they were written to verify (the `requested_provider ->
runtime -> AIAgent kwargs` plumbing).
35 new tests across 5 classes covering every layer of the
GHSA-5qr3-c538-wm9j defence. Each class corresponds to one chokepoint
so a regression in any single layer is caught by the named class:
* ``TestProjectPluginsEnvGate`` (13 cases) — parametrised over both
the documented truthy values (``1`` / ``true`` / ``yes`` / ``on``
+ uppercase variants) and the previously-bypassing falsy strings
(``0`` / ``false`` / ``no`` / ``off`` / ``""`` / ``False``). The
falsy half is the direct env-bypass repro: pre-fix any non-empty
string enabled the project source.
* ``TestApiPathSanitizer`` (16 cases) — unit-level coverage of the
new ``_safe_plugin_api_relpath`` helper. Absolute paths
(``/etc/passwd``, ``/tmp/payload.py``, ``/usr/bin/python``),
``..``-traversal payloads (including nested ``subdir/../../..``),
and non-string / empty / whitespace-only values must all return
``None``. Safe relative paths (``api.py``, ``backend/routes.py``)
round-trip unchanged so legitimate plugins keep working.
* ``TestDiscoveryScrubsApiField`` (3 cases) — end-to-end through
``_discover_dashboard_plugins`` with a real manifest on disk.
Verifies that the cached plugin entry's ``_api_file`` is
scrubbed *at discovery time* (``None`` + ``has_api: False``) so
any downstream consumer can't be tricked into re-deriving the
unsafe path from cache.
* ``TestMountApiRoutesRefusesUntrusted`` (3 cases) — pokes
synthetic plugin entries with each refusal vector directly into
the cache and patches ``importlib.util.spec_from_file_location``
to assert it is *not* invoked for project-source / traversal
payloads, and *is* invoked normally for bundled / user plugins.
* ``TestEndToEndPocBlocked`` (1 case) — reproduces the original
advisory PoC: operator sets ``HERMES_ENABLE_PROJECT_PLUGINS=0``
believing project plugins are off, attacker plants a manifest in
CWD's ``.hermes/plugins/`` with ``api`` pointing at an absolute
payload path. Asserts that the importer is never called against
the payload path *and* that ``hermes_dashboard_plugin_evil`` is
not in ``sys.modules`` after the mount routine runs.
An autouse fixture busts ``_dashboard_plugins_cache`` before and
after each test so the production cache (populated by the
import-time ``_mount_plugin_api_routes()`` call) can't bleed in.
All 12 pre-existing dashboard-plugin tests in
``test_web_server.py`` still pass unchanged.
Extends @briandevans's PR #17659 from {auth.json, auth.lock,
.anthropic_oauth.json} to also cover:
- HERMES_HOME/.env (provider API keys)
- HERMES_HOME/webhook_subscriptions.json (per-route HMAC secrets)
- HERMES_HOME/mcp-tokens/ (OAuth token directory; dir
+ everything inside)
…AND iterates over both _hermes_home_path() AND _hermes_root_path()
so profile-mode runs (HERMES_HOME = <root>/profiles/<name>) also block
<root>/{auth.json, .env, mcp-tokens/, ...}. Same widening shape as the
write-deny side already does (#15981, #14157).
Explicitly NOT a security boundary. Per the personal-assistant trust
model, the terminal tool runs as the same OS user and can `cat
auth.json` directly. This read-deny exists as defense-in-depth:
- Models that respect tool denials empirically tend to stop rather
than reach for the shell.
- The denial surfaces an audit trail when something tries to read
credentials — easier to spot in logs than a generic `cat`.
Docstring + error message both flag this as defense-in-depth so future
contributors don't mistake it for a real security boundary and don't
re-decline reports that propose the same fix shape.
Absorbs the .env and mcp-tokens/ coverage from @tomqiaozc's parallel
PR #8055 (closed-as-duplicate, credited).
Co-authored-by: Tom Qiao <zqiao@microsoft.com>
read_file_tool resolves relative paths against TERMINAL_CWD (or the
task's live terminal cwd), but the prior call passed the original
unresolved string to get_read_block_error. That function's own
resolve() is anchored at the Python process cwd, so when a task's
TERMINAL_CWD pointed at HERMES_HOME and the agent issued read_file
on the relative path "auth.json", the credential-store denylist was
never reached and the file was read normally.
Pass the already-resolved absolute path string at the file_tools call
site, document the contract on get_read_block_error, and add a
read_file_tool-level regression test that pins the relative-path
case under TERMINAL_CWD == HERMES_HOME.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`get_read_block_error` previously only denied reads inside
`${HERMES_HOME}/skills/.hub`, which left `auth.json` (provider OAuth
state + plaintext API keys) and `.anthropic_oauth.json` (Anthropic PKCE
tokens) directly readable by the agent. A prompt-injection reaching
`read_file` could exfiltrate active provider credentials in plaintext.
Mode-0600 file permissions only protect against *other Unix users* —
the agent runs as the file's owner, so `read_file` is unaffected.
Extend the existing deny list with the three credential paths
identified in #17656 (`auth.json`, `auth.lock`, `.anthropic_oauth.json`).
The check uses the same `Path.resolve()` pattern as `skills/.hub`, so
symlink/path-traversal indirection is caught too. The agent doesn't
need to read these directly — `auxiliary_client` and `credential_pool`
consume them through process env / OAuth flows that bypass `read_file`.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
PR #6656 added rel_path + \x00 prefixing to ``bundle_content_hash`` so a
filename swap between two files in a bundle changes the digest. But it
only patched the in-memory side — ``content_hash`` in ``tools/skills_guard.py``
(the on-disk equivalent) still hashed file contents only.
These two functions need to stay symmetric: ``check_for_skill_updates``
compares the disk hash of an installed skill against the bundle hash
of the upstream copy. With the asymmetric fix, every clean install
showed as drifted because the digests no longer matched
(2 existing tests in ``test_skills_hub.py`` started failing as soon as
the contributor's change landed).
Apply the same ``rel_path + \x00 + content`` shape to the disk-side
function. Both functions now produce the same digest for the same skill
content laid out two ways. Documented the symmetry invariant in the
docstring so a future change to either function knows to touch both.
Also adds tests/tools/test_pr_6656_regressions.py with 10 regression
tests covering all three fixes salvaged in PR #6656:
- uninstall_skill path traversal (4 cases: parent segments, absolute
paths, symlink escape, legitimate skill)
- bundle_content_hash filename swap detection (4 cases: in-memory
swap, identity, disk-side swap, bundle↔disk symmetry)
- list_pending lock contract (2 cases: source-grep contract, smoke)
Also fixes AUTHOR_MAP entry for @aaronlab — their commit email
(1115117931@qq.com) maps to "aaronagent" which isn't a real GitHub
login, so changelog @mentions would 404.
Follow-up to PR #28832 — the dashboard plugin routes now accept slashed
names like `observability/langfuse` and `image_gen/openai`, but
`_sanitize_plugin_name` still rejected forward slash and so dashboard
update + remove on those plugins fell through to '404 not found' even
though they exist on disk.
Adds an opt-in `allow_subdir=True` flag that:
- Permits internal forward slashes (category-namespaced plugin keys
emitted by `_discover_all_plugins`).
- Strips leading and trailing slashes.
- Still rejects `..` and backslash, and still asserts the resolved
target lives inside `plugins_dir`.
Opted in at the two read-paths that operate on installed plugins:
`_require_installed_plugin` (CLI update/remove) and
`_user_installed_plugin_dir` (dashboard update/remove). The install
path keeps the default (`allow_subdir=False`) because freshly-cloned
plugins always land top-level under `~/.hermes/plugins/<name>/`.
Adds 6 targeted unit tests covering the new flag's allow/reject matrix.
- test_browser_secret_exfil: mock _run_browser_command instead of
launching real Chrome (secret check is pre-launch, browser is
irrelevant to the assertion)
- test_web_server: add time.sleep(0.05) after pub.send_text() to
yield the event loop before receive_text(). TestClient's sync mode
can race the broadcast handler otherwise, hanging the test.
* fix(minimax-oauth): refresh short-lived access tokens per request
MiniMax OAuth issues ~15-minute access tokens. The Anthropic SDK caches
api_key as a static string at client construction, so a session that
resolves credentials once at startup keeps sending the same bearer until
MiniMax returns 401 mid-session.
Swap the static string for a callable token provider, reusing the existing
Entra-ID bearer-hook infrastructure in build_anthropic_client. The callable
re-reads auth.json on each invocation and calls _refresh_minimax_oauth_state,
which is a no-op when the token still has more than 60s of life left and
refreshes proactively otherwise. Refreshes persist to auth.json so other
processes (gateway, cron) see them immediately.
The wire-up lives at the agent-init / model-switch boundary rather than in
resolve_runtime_provider, so aux client paths that hand the api_key string
to OpenAI(api_key=...) are unaffected.
* docs: add infographic for minimax-oauth token refresh
First migration of an existing built-in platform adapter to the plugin
system established by IRC / Teams / LINE / Google Chat. Closes#24325;
advances the umbrella refactor in #3823.
Matches Teams' shape exactly — adapter under ``plugins/platforms/discord/``
with the standard ``__init__.py`` / ``adapter.py`` / ``plugin.yaml``
shell, ``register(ctx)`` entry point, **no back-compat shim** at the old
import path, and full parity for the four hooks Teams uses plus the
``apply_yaml_config_fn`` hook that landed in #25443 (the Discord plugin
is the first consumer of that hook):
* ``standalone_sender_fn`` — out-of-process cron delivery via REST API
* ``setup_fn`` — interactive ``hermes setup gateway`` wizard
* ``apply_yaml_config_fn`` — translate ``config.yaml`` ``discord:`` keys
into ``DISCORD_*`` env vars (replaces the hardcoded block in
``gateway/config.py``)
* ``is_connected`` — declares connection state from ``DISCORD_BOT_TOKEN``
* ``check_fn`` — lazy-installs ``discord.py`` on demand
* plus ``allowed_users_env``, ``allow_all_env``, ``cron_deliver_env_var``,
``max_message_length``, ``emoji``, ``required_env``, ``install_hint``
* ``gateway/platforms/discord.py`` (5,101 LOC) →
``plugins/platforms/discord/adapter.py`` (git rename, R090).
* New ``plugins/platforms/discord/{__init__.py, plugin.yaml}`` with
``requires_env`` / ``optional_env`` declarations.
* Append ``register(ctx)`` block + new hook implementations
(``_standalone_send``, ``interactive_setup``, ``_apply_yaml_config``,
``_clean_discord_user_ids``, ``_is_connected``, ``_build_adapter``,
plus helpers ``_DISCORD_CHANNEL_TYPE_PROBE_CACHE`` etc.) to the
adapter.
* Replace the ``Platform.DISCORD elif`` branch in
``GatewayRunner._create_adapter()`` (−9 LOC) with a generic post-creation
hook (+6 LOC) in the registry path: any plugin adapter that declares a
``gateway_runner`` attribute now gets it auto-injected. Webhook's
built-in branch is unchanged (it doesn't go through the registry path).
* Move ``_send_discord`` (190 LOC) and helpers
(``_DISCORD_CHANNEL_TYPE_PROBE_CACHE``, ``_remember_channel_is_forum``,
``_probe_is_forum_cached``, ``_derive_forum_thread_name``) from
``tools/send_message_tool.py`` into the plugin as ``_standalone_send``.
* Wire via ``standalone_sender_fn=_standalone_send`` (Teams pattern; same
gap fixed in #21804 for other plugin platforms).
* Replace the Discord ``elif`` in ``tools/send_message_tool.py``
``_send_to_platform`` with a 10-line registry-hook dispatch.
* Drop the ``DiscordAdapter`` import and the
``Platform.DISCORD: DiscordAdapter.MAX_MESSAGE_LENGTH`` ``_MAX_LENGTHS``
entry — the registry's ``max_message_length=2000`` covers it.
* Move ``_setup_discord`` and ``_clean_discord_user_ids`` (68 LOC) from
``hermes_cli/setup.py`` into the plugin as ``interactive_setup``.
* Wire via ``setup_fn=interactive_setup``. CLI helpers (``prompt``,
``print_info``, etc.) are lazy-imported so the plugin's module-load
surface stays minimal.
* Remove ``"discord": _s._setup_discord`` from
``hermes_cli/gateway.py::_builtin_setup_fn``.
* Remove the entire 32-line ``_PLATFORMS["discord"]`` static dict entry —
Discord's setup metadata is now discovered dynamically via
``_all_platforms()`` from the registry entry.
* Move the 59-line ``discord_cfg`` YAML→env bridge from
``gateway/config.py::load_gateway_config()`` into the plugin as
``_apply_yaml_config``. Covers ``require_mention``,
``thread_require_mention``, ``free_response_channels``, ``auto_thread``,
``reactions``, ``ignored_channels``, ``allowed_channels``,
``no_thread_channels``, ``allow_mentions.{everyone,roles,users,
replied_user}``, and ``reply_to_mode`` (including the YAML 1.1
``off``-as-False coercion and the ``extra.reply_to_mode`` fallback).
* Wire via ``apply_yaml_config_fn=_apply_yaml_config``.
* The hook runs BEFORE ``_apply_env_overrides`` and after the generic
shared-key loop, exactly as documented in
``website/docs/developer-guide/adding-platform-adapters.md``.
* Behavior is preserved exactly — every assignment still uses
``not os.getenv(...)`` guards so env vars take precedence over YAML.
All 78 references to the old import path are rewritten — no back-compat
shim:
* 51 ``from gateway.platforms.discord import X`` →
``from plugins.platforms.discord.adapter import X``
* 5 ``import gateway.platforms.discord as discord_platform`` →
``import plugins.platforms.discord.adapter as discord_platform``
* 1 ``from gateway.platforms import discord as discord_mod`` →
``from plugins.platforms.discord import adapter as discord_mod``
* 21 ``mock.patch("gateway.platforms.discord.X")`` strings →
``mock.patch("plugins.platforms.discord.adapter.X")``
* 1 docstring reference in ``hermes_cli/commands.py``
* 1 import in ``tools/send_message_tool.py`` (now removed entirely)
The import-safety test in ``tests/gateway/test_discord_imports.py`` is
updated to purge the new canonical module name from ``sys.modules``.
**38 files changed, +621 / −473** — net positive due to the YAML hook
implementation (89 new LOC in the plugin trading for 59 deleted in core),
but every line moved has a clear plugin home now. The git rename is
detected at R090 because the adapter gained ~340 LOC of moved-in hook
implementations (``_standalone_send`` + ``interactive_setup`` +
``_apply_yaml_config`` + helpers).
* All 568 Discord-specific tests pass across 25 ``test_discord_*.py``
files plus voice/send/text-batching/reload-skills/stream-consumer/
integration tests.
* All 147 tests in the YAML-touching subset
(``test_discord_reply_mode``, ``test_discord_free_response``,
``test_discord_allowed_channels``, ``test_discord_allowed_mentions``,
``test_discord_channel_controls``, ``test_discord_reactions``,
``test_discord_thread_persistence``, ``test_runtime_footer``) pass —
this is the strongest signal that the YAML→env hook behaves
identically to the legacy block.
* Broader gateway/cron/integration sweep (1297 tests) introduces zero
new failures vs ``main``. Pre-existing failures in
``tests/gateway/test_tts_media_routing.py`` and
``tests/e2e/test_platform_commands.py`` reproduce identically on the
unchanged ``main`` revision.
* Plugin discovery sanity check confirms Discord registers alongside the
other four platform plugins:
Registered platforms: ['discord', 'google_chat', 'irc', 'line', 'teams']
These Discord-shaped tendrils in core were **deliberately not moved** —
they are generic platform-registry concerns affecting every platform,
not Discord-specific:
* ``gateway/config.py:1205`` ``DISCORD_BOT_TOKEN → config.token`` env
enablement — same shape Telegram has. The existing
``env_enablement_fn`` registry hook only seeds ``extra``, not
``.token``, so it can't replace this without an adapter refactor to
read from ``extra["bot_token"]``.
* ``gateway/run.py`` voice-mode hooks
(``self.adapters.get(Platform.DISCORD)`` for
``start_voice_mode``/``stop_voice_mode``), role-based auth,
``DISCORD_ALLOW_BOTS`` branch in ``_is_user_authorized``,
``_UPDATE_ALLOWED_PLATFORMS`` frozenset, and the per-platform
allowlist maps — generic platform-registry concerns.
* ``Platform.DISCORD`` enum literal — stable identifier used as dict
keys throughout the codebase; removing it is a separate refactor with
no real benefit.
* ``tools/discord_tool.py`` and ``tools/environments/local.py`` —
first-class agent tools and env-passthrough config, neither is the
gateway adapter.
Each of these is worth its own scoping issue when the time comes.
@memosr's PR #27612 put the inference_base_url allowlist check only at the
Nous proxy adapter forward boundary. The poisoned URL, however, lands in
``auth.json`` upstream of that — at five refresh / agent-key-mint payload
read sites inside ``resolve_nous_runtime_credentials`` and
``_extend_state_from_refresh``. Without gating those sites, a single MITM
on a refresh response persists the attacker's URL across restarts, even
if the proxy adapter's defense-in-depth check would later catch it on
the way out.
Replace ``_optional_base_url`` with ``_validate_nous_inference_url_from_network``
at all five Portal-network reads:
- hermes_cli/auth.py L4840 (refresh-only access-token path)
- hermes_cli/auth.py L4876 (mint payload path)
- hermes_cli/auth.py L5154 (terminal-runtime access-token refresh)
- hermes_cli/auth.py L5262 (cross-process serialized refresh)
- hermes_cli/auth.py L5317 (terminal-runtime mint payload)
The state-read path at L5025 (``state.get("inference_base_url")``) is
deliberately NOT gated — pre-existing state in ``auth.json`` is either
already validated (it came from one of the five network sites above) or
set by a trusted local actor (manual edit, ``_setup_nous_auth`` test
fixture, ``hermes login nous`` against a staging endpoint via the
documented ``NOUS_INFERENCE_BASE_URL`` env override). Direct write_file /
patch tampering with auth.json is independently blocked by PR #14157.
Adds tests/hermes_cli/test_nous_inference_url_validation.py covering:
- validator https + host + edge-case rules (12 cases)
- all 5 network call sites grep contracts (no _optional_base_url
regression possible without test failure)
- proxy adapter defense-in-depth check still present
- env override path NOT gated (documented dev/staging behaviour)
18 new tests, all 119 Nous-auth tests green.
PR #14157 added control-plane write-deny against the ACTIVE HERMES_HOME,
which is fine in non-profile mode but leaves a gap once a profile is
active: HERMES_HOME points at <root>/profiles/<name>, so the global
<root>/auth.json + <root>/config.yaml + <root>/webhook_subscriptions.json
+ <root>/mcp-tokens/ remain writable. Same shape as the .env gap PR
#15981 closed via _hermes_root_path().
Apply the same widening pattern here. The control-file/mcp-tokens check
now iterates BOTH _hermes_home_path() and _hermes_root_path() (dedupes
when they coincide in non-profile mode). Also tightens the mcp-tokens
check from "startswith dir + os.sep" to "==dir OR startswith dir + os.sep"
so writing the directory entry itself is blocked, not just files inside.
Regression tests cover both protections in a real profile-mode layout
(<tmp>/hermes/profiles/coder as HERMES_HOME, <tmp>/hermes as root).
Adds active-HERMES_HOME control-plane files to the write deny list:
auth.json, config.yaml, webhook_subscriptions.json, and any path
under mcp-tokens/. realpath() resolves before comparison so
directory-traversal and symlink targets are normalised, preventing
trivial deny-list bypass via ../ tricks.
Without this, a prompt-injected agent could rewrite Hermes' own
auth state or routing config via write_file / patch — without
triggering the terminal dangerous-command approval — and persist
attacker-controlled behaviour across sessions.
Fixes#14072
When an existing install upgrades to the hashed-pending schema, its
on-disk pending.json still has the old {code: entry} format with no
hash/salt fields. The original PR #8056 assumed every entry had both
fields and would have KeyErrored in approve_code, list_pending, and
_cleanup_expired.
Guard each consumer:
- approve_code: skip entries that are not a dict, lack salt/hash,
or have a non-hex salt. Legacy entries simply fail to match.
- list_pending: tolerate missing 'hash' (show "legacy" placeholder)
and non-numeric created_at (skip the row).
- _cleanup_expired: treat malformed/legacy entries as expired so
they get pruned on the next call rather than wedging the file.
Regression tests cover all three consumers plus a mixed-malformed
case.
Pairing codes were stored as plaintext keys in JSON files. Now uses
sha256 + random salt hashing with constant-time comparison.
Fixes#8036
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Mirrors the architecture established by the web (#25182), browser
(#25214), and video_gen (#25126) plugin migrations:
* `tools/fal_common.py` — stateless atoms shared by both FAL-backed
plugins (image_gen + video_gen). Holds the lazy `fal_client` import
helper, `_ManagedFalSyncClient`, `_normalize_fal_queue_url_format`,
`_extract_http_status`. Stateful pieces (`fal_client` module global,
`_managed_fal_client*` cache, `_submit_fal_request`,
`_resolve_managed_fal_gateway`, `_get_managed_fal_client`)
intentionally stay on `tools.image_generation_tool` so the existing
`monkeypatch.setattr(image_tool, ...)` patch sites keep working
unchanged.
* `plugins/video_gen/fal/__init__.py` — drops its inline
`_load_fal_client` duplicate; consumes `tools.fal_common.import_fal_client`.
* `plugins/image_gen/fal/{plugin.yaml,__init__.py}` — new plugin.
`FalImageGenProvider` is a thin registration adapter that resolves
the legacy module via `import tools.image_generation_tool as _it`
and calls `_it.image_generate_tool` + `_it._resolve_fal_model` at
call time. The 18-model catalog, `_build_fal_payload`, managed-
gateway selection, and Clarity Upscaler chaining all remain in
`tools.image_generation_tool` as the single source of truth —
the plugin is a registration adapter, not a parallel implementation.
* `tools/image_generation_tool.py::_dispatch_to_plugin_provider` —
drops the `configured == "fal"` skip. Setting `image_gen.provider:
fal` now routes through the registry like any other provider; the
plugin re-enters this module's pipeline so behavior is identical.
Unset `image_gen.provider` still falls through to the in-tree
pipeline (preserves no-config-with-FAL_KEY UX from #15696).
* `hermes_cli/tools_config.py` — drops the hardcoded "FAL.ai" row from
`TOOL_CATEGORIES["image_gen"]["providers"]` (now injected by
`_plugin_image_gen_providers` like every other backend) and the
`getattr(provider, "name") == "fal"` skip that protected against
duplication with the hardcoded row. The "Nous Subscription" row
stays as a setup-flow entry — same shape browser kept "Nous
Subscription (Browser Use cloud)" after #25214.
* `tests/plugins/image_gen/test_fal_provider.py` — 14 cases covering
the ABC surface, call-time indirection (verifying
`monkeypatch.setattr(image_tool, "image_generate_tool", ...)` takes
effect through the plugin), response-shape stamping, exception
handling, and registry wiring.
* `tests/plugins/image_gen/check_parity_vs_main.py` — subprocess
harness mirroring `tests/plugins/browser/check_parity_vs_main.py`.
Pins one path to origin/main, one to the worktree; runs six
scenarios (unset, explicit-fal-no-creds, explicit-fal-with-creds,
explicit-fal-with-model, typo provider, managed-gateway-only) and
diffs the reduced shape `{dispatch_kind, provider_name, model}`
per scenario. The only acceptable diff is "legacy_fal → plugin
(fal)" for explicit-FAL paths — every other delta is flagged as
a regression.
* `tests/hermes_cli/test_image_gen_picker.py::test_fal_surfaced_alongside_other_plugins`
— flips the previous `test_fal_skipped_to_avoid_duplicate` to
match the new shape (FAL is a plugin now, no dedup needed).
Verified: 195/195 tests across
`tests/{tools/test_image_generation*,tools/test_managed_media_gateways,plugins/image_gen,plugins/video_gen,hermes_cli/test_image_gen_picker}.py`
pass on this branch with no test patches modified outside the picker
test that asserted the old skip behaviour.
Fixes#26241
Covers _reload_dynamic_routes() rejecting empty or missing per-route
secrets when no global fallback exists, preserving the INSECURE_NO_AUTH
opt-in, inheriting a global secret when only the per-route value is
missing, and partial-skip when only one of multiple routes is bad.
Move the autouse `_disable_lazy_stt_install` fixture out of the three
transcription test files and into `tests/tools/conftest.py` as a regular
(non-autouse) fixture. Each transcription test module opts in once at
the top via `pytestmark = pytest.mark.usefixtures(...)`.
Why: addresses three Copilot inline review comments on this PR that
flagged the verbatim duplication across files. Centralizing also keeps
the patch target in a single place, so a future rename of
`_try_lazy_install_stt` only updates one location.
Why opt-in (not autouse in conftest): other `tests/tools/` files do not
patch `_HAS_FASTER_WHISPER` and have no reason to bypass the runtime
lazy-install probe; making the fixture autouse globally would silently
mask any future test that wants to exercise the real lazy-install path.
`b5c6d9ac0` ("fix: wire STT lazy-install into transcription_tools.py")
added `_try_lazy_install_stt()`, which calls
`importlib.util.find_spec("faster_whisper")` after `ensure()` runs.
In the dev / CI environment `faster_whisper` is already installed, so
the probe returns truthy and `_get_provider()` returns "local" even
when the test has patched `_HAS_FASTER_WHISPER=False` to simulate
"not installed".
Add a per-file autouse fixture that patches `_try_lazy_install_stt`
to return False so the simulation stays accurate. The 16 baseline
failures across `test_transcription_tools.py`,
`test_transcription.py`, and `test_transcription_dotenv_fallback.py`
disappear; the production lazy-install path is unaffected at runtime.
When Bitwarden Secrets Manager supplies a provider key, 'hermes model'
and the setup wizard show 'credentials ✓' with no hint of where the
key came from — identical to the .env case. Users assume the integration
isn't wired up and re-enter the key (or hit Enter and cancel).
env_loader now tracks which env vars were injected by an external secret
source and exposes get_secret_source() / format_secret_source_suffix() so
the provider flows can render 'Anthropic credentials: sk-ant-... ✓
(from Bitwarden)' instead of an unlabeled checkmark.
Wired into _prompt_api_key (kimi, z.ai, minimax, opencode, ...), the
Anthropic provider flow, the Bedrock flow, and the GitHub Copilot token
display.
Future secret sources (Vault, 1Password, etc.) drop in by setting their
own label in _SECRET_SOURCES; format_secret_source_suffix() has a generic
fallback so no call sites need updating.
_maybe_follow_capture() issued a follow-up screenshot unconditionally
when capture_after=True, even when res.ok=False. The model then received
a normal-looking screenshot alongside an error message, and in practice
it often ignored ok=False and proceeded as if the action had succeeded.
Fix: return _text_response(res) early when res.ok is False so the model
receives only the error and can decide how to recover.
Tests added:
- test_capture_after_skipped_when_action_failed: patches click to return
ok=False and asserts no capture call is issued.
- test_capture_after_fires_when_action_succeeds: ensures the happy path
still triggers the follow-up capture.
_dispatch() routes action="set_value" to backend.set_value(), but:
- ComputerUseBackend did not declare set_value as @abstractmethod, so
subclasses could silently omit it without a TypeError at class load time.
- _NoopBackend (the test/CI stub) had no set_value method at all, causing
AttributeError in any test that exercises the set_value action path.
Fix:
- Add set_value as @abstractmethod to ComputerUseBackend in backend.py.
- Add a recording stub in _NoopBackend in tool.py.
- Add two TestDispatch cases: one verifying the call reaches the backend,
one verifying the missing-value guard returns a clean error.
