Follow-up to the previous commit:
- Add _is_loopback_host() helper covering 127.0.0.1, localhost, ::1,
ip6-localhost, ip6-loopback (case-insensitive). Empty/None host is
treated as non-loopback since unset usually means public default bind.
- Fix mixed-indent comment in the safety rail (comment now aligned with
the if-block) and collapse the nested-if into one condition.
- Add TestInsecureNoAuthSafetyRail covering rejection on 0.0.0.0, a LAN
IP, and empty host; allowance on 127.0.0.1/localhost; plus unit-level
parametrized coverage of _is_loopback_host for spellings we can't bind
in the hermetic test env (::1, ip6-localhost, ip6-loopback).
- Pin test_connect_starts_server + test_webhook_deliver_only defaults
to 127.0.0.1 so they keep passing under the new rail.
- Document the behavior in website/docs/user-guide/messaging/webhooks.md.
Following PR #21306 which added the new generic plugin-platform hooks,
update the three platform-authoring docs so plugin authors find them:
- website/docs/developer-guide/adding-platform-adapters.md: expand the
'What the Plugin System Handles Automatically' table with env-only
auto-enable + cron delivery + hermes-config UI entries rows. Add
three new sections — 'Env-Driven Auto-Configuration', 'Cron
Delivery', 'Surfacing Env Vars in hermes config' — covering the
hook signatures, plugin.yaml rich-dict format, and the
home_channel-key special case. Update the main register() example
to pass env_enablement_fn + cron_deliver_env_var inline so readers
see them on their first pass. Upgrade the PLUGIN.yaml snippet to
show bare-string + rich-dict + optional_env.
- website/docs/guides/build-a-hermes-plugin.md: the thin platform
example in the build-a-plugin tour now includes env_enablement_fn
and cron_deliver_env_var, plus an optional_env block in the inline
plugin.yaml. Keeps pointing to the developer-guide page for the
full treatment.
- gateway/platforms/ADDING_A_PLATFORM.md: the in-repo reference
shallow-points at the docsite but now names the three new hooks
explicitly so contributors reading the source tree know what
they're for. Also adds teams + google_chat as reference
implementations alongside irc.
When a user replies while quoting another message, QQ sets
'message_type = 103' and pushes the referenced message's content +
attachments inside 'msg_elements[0]'. The old adapter ignored
msg_elements entirely, so:
- Bare quote-replies (no user text) surfaced nothing to the LLM.
- Quoted images/files/voice were never downloaded or described.
- Quoted voice messages specifically produced no transcript — the model
had no way to see what the user was referring to when saying 'about
this voice note…'.
This commit adds _process_quoted_context(d) which extracts msg_elements,
unions their attachments, and runs them through the SAME
_process_attachments pipeline as the main message body. Quoted voice
gets an STT transcript (tried via QQ's asr_refer_text first, then the
configured STT provider); quoted images get cached just like main-body
images; quoted files surface with their original filename intact (not
the CDN URL hash).
The quoted content is prepended to the user's text as a '[Quoted message]:'
block so the LLM sees the full referential context on one turn.
Images-only quotes surface a '[Quoted message]: (image)' marker so the
model knows an image was referenced even if no text came with it.
All four inbound handlers (_handle_c2c_message, _handle_group_message,
_handle_guild_message, _handle_dm_message) now call the helper uniformly
— one merge pattern, not four divergent implementations.
Filename preservation is carried by _process_attachments' existing
'[Attachment: {filename or ct}]' line; nothing else needed for that.
12 new tests under TestProcessQuotedContext and TestMergeQuoteInto cover:
- Non-quote messages short-circuit to empty
- message_type=103 with no msg_elements is harmless
- Text-only quotes render with '[Quoted message]:' prefix
- Voice attachments in the quote flow through STT
- File attachments in the quote preserve the original filename
- Image attachments surface cached paths + media types
- Images-only quote still emits a marker
- Multiple msg_elements are concatenated
- Malformed message_type values return empty
- _merge_quote_into prepends with a blank-line separator
Full qqbot suite: 130 passed (72 existing + 19 chunked + 27 keyboards
+ 12 quoted).
Co-authored-by: WideLee <limkuan24@gmail.com>
The QQ Bot v2 API supports inline keyboards on outbound messages. When a
user taps a button, the platform dispatches an INTERACTION_CREATE
gateway event; the bot ACKs it via PUT /interactions/{id} and decodes
the button's data payload to route the click.
This commit adds:
New module gateway/platforms/qqbot/keyboards.py
- Inline-keyboard dataclasses (InlineKeyboard, KeyboardRow, KeyboardButton,
KeyboardButtonAction, KeyboardButtonRenderData, KeyboardButtonPermission)
that serialize to the JSON shape the QQ API expects.
- build_approval_keyboard(session_key) — 3-button layout:
✅ 允许一次 / ⭐ 始终允许 / ❌ 拒绝, all sharing group_id='approval'
so clicking one greys out the rest.
- build_update_prompt_keyboard() — Yes/No keyboard for update confirms.
- parse_approval_button_data() / parse_update_prompt_button_data() —
decode the button_data payload from INTERACTION_CREATE.
approve:<session_key>:<decision> (decision = allow-once|allow-always|deny)
update_prompt:<answer> (answer = y|n)
- build_approval_text(ApprovalRequest) — markdown renderer for the
surrounding message body (exec-approval and plugin-approval variants,
with severity icons 🔴/🔵/🟡).
- parse_interaction_event(raw) → InteractionEvent dataclass — normalizes
the nested raw payload (id / scene / openids / button_data / etc.).
Adapter changes (gateway/platforms/qqbot/adapter.py)
- _dispatch_payload routes INTERACTION_CREATE → _on_interaction.
- _on_interaction parses the event, ACKs via PUT /interactions/{id}, then
invokes a user-registered interaction callback. Exceptions from the
callback are caught and logged (never propagate into the WS loop).
- set_interaction_callback(cb) lets gateway wiring register a routing
handler that inspects button_data and resolves the corresponding
pending approval / update prompt.
- _send_c2c_text / _send_group_text now accept an optional keyboard kwarg
and append it to the outbound body.
- send_with_keyboard(chat_id, content, keyboard, reply_to=None) — public
helper that sends a single short message with a keyboard attached.
Does NOT chunk-split (a keyboard message has one interactive surface).
Guild chats are rejected non-retryably — they don't support keyboards.
- send_approval_request(chat_id, ApprovalRequest, reply_to=None) +
send_update_prompt(chat_id, content, reply_to=None) — convenience
wrappers over send_with_keyboard.
Tests
27 new unit tests under TestApprovalButtonData, TestUpdatePromptButtonData,
TestBuildApprovalKeyboard, TestBuildUpdatePromptKeyboard, TestBuildApprovalText,
TestInteractionEventParsing, and TestAdapterInteractionDispatch. Cover:
- Button-data round-trip (build → parse returns original session/decision)
- Keyboard JSON shape + mutual-exclusion group_id
- Exec vs plugin approval text templates + severity icons
- Interaction event parsing (c2c / group / guild scene codes)
- _on_interaction end-to-end: ACK invoked, callback receives parsed event,
callback exceptions are swallowed, missing id skips ACK, no registered
callback is harmless.
Full qqbot suite: 118 passed (72 existing + 19 chunked + 27 keyboards).
Co-authored-by: WideLee <limkuan24@gmail.com>
The v2 'single POST /v2/{users|groups}/{id}/files' upload path is capped
at ~10 MB inline (base64 'file_data' or 'url'). For larger files the QQ
platform provides a three-step flow:
1. POST /upload_prepare → upload_id + pre-signed COS part URLs
2. PUT each part to its COS URL → POST /upload_part_finish
3. POST /files with {upload_id} → file_info token
This commit adds a new gateway/platforms/qqbot/chunked_upload.py module
that implements the flow, wires it into QQAdapter._send_media for local
files (URL uploads keep the existing inline path), and introduces
structured exceptions so the caller can surface actionable error text:
- UploadDailyLimitExceededError (biz_code 40093002, non-retryable)
- UploadFileTooLargeError (file exceeds the platform limit)
Both carry file_name / file_size_human / limit_human so the model can
compose user-friendly replies instead of seeing opaque HTTP codes.
The part_finish 40093001 retryable-error loop respects the server-
provided retry_timeout (capped at 10 minutes locally) with a 1 s
polling interval. COS PUTs retry transient failures up to 2 times
with exponential backoff. complete_upload retries up to 2 times.
Covers files up to the platform's ~100 MB per-file limit; before this
the adapter silently rejected anything over ~10 MB.
19 new unit tests under TestChunkedUpload* cover the happy path,
prepare-response parsing, helper functions, part retries, COS PUT
retries, group vs c2c routing, and the structured-error mapping.
Co-authored-by: WideLee <limkuan24@gmail.com>
Adds a per-task override for the consecutive-failure circuit breaker,
so individual tasks can opt out of the global ``kanban.failure_limit``
without dragging everyone else with them.
Resolution order (now three tiers):
1. per-task ``max_retries`` (new, this commit)
2. caller-supplied ``failure_limit`` — the gateway threads
``kanban.failure_limit`` from config here
3. ``DEFAULT_FAILURE_LIMIT`` (2)
Changes:
- ``tasks.max_retries INTEGER`` column + migration for existing DBs
(NULL = no override, matches pre-column behavior).
- ``Task.max_retries`` field + ``from_row`` plumbing.
- ``create_task(..., max_retries=N)`` kwarg.
- ``_record_task_failure`` reads the per-task value first and records
``limit_source`` + ``effective_limit`` on the ``gave_up`` event so
operators can see which tier won.
- CLI: ``hermes kanban create --max-retries N`` (rejects ``< 1``).
- CLI: ``hermes kanban show`` surfaces the effective threshold +
source (``(task)``, ``(config kanban.failure_limit)``, ``(default)``).
- CLI: ``_task_to_dict`` includes ``max_retries`` in ``--json`` output.
Key design choice vs. the earlier #20972 attempt:
- No new config key. The existing ``kanban.failure_limit`` (landed in
#21183) is the dispatcher-tier source — no silent break for users
who already tuned it.
- No ``!=`` sentinel for "is config set" (which would misfire when
config equals the default). The tier-winner is determined purely
by "is per-task override set" — the dispatcher always wins when
per-task is NULL, regardless of whether the caller passed the
default or a configured value.
E2E verified across four scenarios: default-only (trips at 2),
config-only (trips at caller's value), per-task-only beats default
(trips at task value), per-task beats larger config (trips at task
value). ``gave_up`` event metadata correctly records ``limit_source``
and ``effective_limit`` in all cases.
Tests:
- ``test_per_task_max_retries_overrides_dispatcher_limit`` — task=1
beats caller=10.
- ``test_per_task_max_retries_allows_more_than_default`` — task=5
does not trip at caller=default of 2.
- ``test_max_retries_none_falls_through_to_dispatcher_limit`` — None
honors caller's config value (4), records ``limit_source=dispatcher``.
Full kanban trio (db + core + cli + tools + dashboard-plugin): 342
passed, no regressions.
Supersedes: #20972 (@jelrod27) — credit in PR close comment.
Ref: #20263 (tangentially — the reporter asked about adapter API
drift, not retry caps, but the CLI discussion there is what
surfaced the original ask).
PairingStore.approve_code() didn't consult _is_locked_out(), so after
MAX_FAILED_ATTEMPTS bad approvals the lockout flag was set but a valid
code still got accepted — any pending code (legitimately issued or
attacker-obtained) could be approved during the 1-hour lockout window,
nullifying the brute-force protection.
- gateway/pairing.py: lockout check runs in approve_code() right after
_cleanup_expired, before the pending lookup. Returns None on lockout.
- tests/gateway/test_pairing.py: test_lockout_blocks_code_approval pins
the regression — reporter's exact reproducer (generate valid code,
exhaust attempts with WRONGCODE, try to approve valid code) must
return None and leave is_approved == False. Also pins recovery: once
lockout expires, the still-pending code approves normally.
- hermes_cli/pairing.py: _cmd_approve distinguishes the two None cases.
On lockout, prints 'Platform locked out... clears in N minutes. To
reset sooner, delete the _lockout:<platform> entry from
_rate_limits.json' instead of the misleading 'Code not found or
expired' message. 29/29 pairing tests pass; E2E-verified with
reporter's exact Python reproducer.
Adopt the generic platform-plugin hooks landed in the preceding commit
so IRC and Teams get env-only config detection and cron home-channel
delivery without living in cron/scheduler.py's hardcoded sets.
IRC (plugins/platforms/irc/):
- adapter.py: new _env_enablement() seeds server, channel, port,
nickname, use_tls, server_password, nickserv_password, and a
home_channel dict into PlatformConfig on env-only setups.
IRC_HOME_CHANNEL defaults to IRC_CHANNEL so deliver=irc cron jobs
route to the joined channel by default.
- adapter.py: register_platform() gains env_enablement_fn=_env_enablement
and cron_deliver_env_var='IRC_HOME_CHANNEL'.
- plugin.yaml: rich requires_env / optional_env with description,
prompt, password, url for every IRC env var. Hardcoded IRC entries
in hermes_cli/config.py still win (back-compat), but the plugin now
carries its own metadata.
Teams (plugins/platforms/teams/):
- adapter.py: new _env_enablement() seeds client_id, client_secret,
tenant_id, port, and home_channel into PlatformConfig. Closes the
long-standing gap where TEAMS_HOME_CHANNEL was documented but never
wired up.
- adapter.py: register_platform() gains env_enablement_fn=_env_enablement
and cron_deliver_env_var='TEAMS_HOME_CHANNEL' — deliver=teams cron
jobs now work.
- plugin.yaml: rich requires_env / optional_env with description,
prompt, password, url for every Teams env var. Surfaces them in
'hermes config' UI for the first time (Teams had no OPTIONAL_ENV_VARS
entries before this).
Zero behavior change for existing users: env_enablement_fn is only
called when env vars are set, and the registry's config-first-env-fallback
path in validate_config / is_connected is unchanged.
Adds Google Chat as a new gateway platform, shipped under
plugins/platforms/google_chat/ following the canonical bundled-plugin
pattern (Teams, IRC). Rewired from the original PR #18425 to use the
new env_enablement_fn + cron_deliver_env_var plugin interfaces landed
in the preceding commit, so the adapter touches ZERO core files.
What it does:
- Inbound DM + group messages via Cloud Pub/Sub pull subscription (no
public URL needed), with attachments (PDFs, images, audio, video)
downloaded through an SSRF-guarded Google-host allowlist.
- Outbound text replies with the 'Hermes is thinking…' patch-in-place
pattern — no tombstones.
- Native file attachment delivery via per-user OAuth. Google Chat's
media.upload endpoint rejects service-account auth, so each user
runs /setup-files once in their own DM to grant
chat.messages.create for themselves; the adapter then uploads as
them. Tokens stored per email at
~/.hermes/google_chat_user_tokens/<email>.json.
- Thread isolation: side-threads get isolated sessions, top-level DM
messages share one continuous session. Persistent thread-count
store survives gateway restart.
- Supervisor reconnect with exponential backoff.
- Multi-user out of the box.
How it plugs in (no core edits):
- env_enablement_fn seeds PlatformConfig.extra with project_id,
subscription_name, service_account_json, and the home_channel dict
(which the core hook turns into a HomeChannel dataclass). Reads
GOOGLE_CHAT_PROJECT_ID (falls back to GOOGLE_CLOUD_PROJECT),
GOOGLE_CHAT_SUBSCRIPTION_NAME (falls back to GOOGLE_CHAT_SUBSCRIPTION),
GOOGLE_CHAT_SERVICE_ACCOUNT_JSON (falls back to
GOOGLE_APPLICATION_CREDENTIALS), GOOGLE_CHAT_HOME_CHANNEL.
- cron_deliver_env_var='GOOGLE_CHAT_HOME_CHANNEL' gets cron delivery
for free — cron/scheduler.py consults the platform registry for any
name not in its hardcoded built-in sets.
- plugin.yaml's rich requires_env / optional_env blocks auto-populate
OPTIONAL_ENV_VARS via the new hermes_cli/config.py injector, so
'hermes config' UI surfaces them with description / url / prompt /
password metadata.
- Module-level Platform('google_chat') call in adapter.py triggers the
Platform._missing_() registration so Platform.GOOGLE_CHAT attribute
access works without an enum entry.
Distribution: ships inside the existing hermes-agent package. Users
opt in via 'pip install hermes-agent[google_chat]' and follow the
8-step GCP walkthrough at
website/docs/user-guide/messaging/google_chat.md.
Test coverage: 153 tests in tests/gateway/test_google_chat.py, all
passing. Spans platform registration, env config loading, Pub/Sub
envelope routing, outbound send + chunking + typing patch-in-place,
attachment send paths, SSRF guard, thread/session model,
supervisor reconnect, authorization, per-user OAuth, and the new
plugin-registry cron delivery wiring.
Credit: adapter + OAuth + tests + docs authored by @donramon77
(PR #18425). Rewire onto the new plugin hooks + salvage commit by
Teknium.
Co-Authored-By: Ramón Fernández <112875006+donramon77@users.noreply.github.com>
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.
MCP tool results can include ImageContent blocks (screenshots from
Playwright/Blockbench/Puppeteer etc). The tool result handler only
extracted block.text, so image blocks were silently dropped and the
agent saw an empty or text-only response — losing the actual payload.
Add _cache_mcp_image_block() that base64-decodes the block, validates
the bytes via gateway.platforms.base.cache_image_from_bytes (which
sniffs for PNG/JPEG/WebP signatures and rejects non-images), writes to
the shared `~/.hermes/cache/images/` dir, and returns a MEDIA:<path>
tag. The handler appends that tag to the result parts so downstream
gateway adapters render the image inline.
Logs and drops on malformed base64 / non-image payload rather than
raising — a single bad block shouldn't kill the tool call.
Distilled from #17915 (c3115644151) and #10848 (gnanirahulnutakki), both
too stale to cherry-pick (branches diverged enough to revert dozens of
unrelated fixes). Went with #10848's approach of plumbing through
Hermes' existing MEDIA tag / cache_image_from_bytes infrastructure
rather than #17915's raw tempfile path, because it integrates with the
remote-backend mount system and messaging adapters that already handle
MEDIA tags natively.
Co-authored-by: c3115644151 <c3115644151@users.noreply.github.com>
Co-authored-by: gnanirahulnutakki <gnanirahulnutakki@users.noreply.github.com>
* fix(mcp): re-raise CancelledError explicitly in MCPServerTask.run
On Python 3.11+, `asyncio.CancelledError` inherits from `BaseException`
(not `Exception`), so the broad `except Exception as exc:` in
`MCPServerTask.run`'s transport loop did NOT catch it. Task cancellation
from gateway restart / explicit `task.cancel()` silently escaped past
the reconnect logic — the MCP server task died without going through
the shutdown/reconnect code paths that check `_shutdown_event`.
Add an explicit `except asyncio.CancelledError: raise` before the broad
catch so cancellation propagation is self-documenting rather than an
accident of exception hierarchy, and future sibling-site work (e.g.
distinguishing shutdown-cancel from transport-cancel) has an obvious
hook. Behavior on pre-3.8 Pythons where CancelledError WAS an Exception
subclass is also corrected: the old path would have caught it and
treated it as a connection failure worth retrying.
Closes#9930.
* fix(mcp): forward OAuth auth and bump sse_read_timeout on SSE transport
Two surgical correctness bugs in the SSE branch of MCPServerTask._run_http,
distilled from @amiller's PR #5981 that couldn't be cherry-picked wholesale
(branch too stale).
1. sse_read_timeout was set to the tool timeout (default 60s). That's the
wrong dimension — it governs how long sse_client will wait between
events on the SSE stream, not per-call latency. SSE servers routinely
hold the stream idle for minutes between events; a 60s read timeout
drops the connection after the first slow stretch (Router Teamwork,
Supermemory on Cloudflare Workers idle-disconnect at ~60s). Bump to
300s to match the Streamable HTTP path's httpx read timeout.
2. OAuth auth was built via get_manager().get_or_build_provider() but
never forwarded to sse_client. SSE MCP servers behind OAuth 2.1 PKCE
would silently fail with 401s on every request.
Keepalive (the other half of #5981) intentionally left for a follow-up —
it's a real improvement but a bigger change, and these two are obvious
corrections to ship now. Credits to @amiller.
Co-authored-by: Andrew Miller <socrates1024@gmail.com>
---------
Co-authored-by: Andrew Miller <socrates1024@gmail.com>
Commit b12a5a72b renamed the local variable resumeId -> resumeParam at
line 157 but left two call sites referencing the old name at lines 555
and 660. tsc -b fails with two TS2304 errors, which tanks npm run build,
which makes `hermes dashboard` print "Web UI build failed" with no
further detail.
Finishes the rename at both call sites instead of re-introducing the
old name via an alias.
Co-authored-by: qiuqfang <qiuqfang98@qq.com>
On Python 3.11+, `asyncio.CancelledError` inherits from `BaseException`
(not `Exception`), so the broad `except Exception as exc:` in
`MCPServerTask.run`'s transport loop did NOT catch it. Task cancellation
from gateway restart / explicit `task.cancel()` silently escaped past
the reconnect logic — the MCP server task died without going through
the shutdown/reconnect code paths that check `_shutdown_event`.
Add an explicit `except asyncio.CancelledError: raise` before the broad
catch so cancellation propagation is self-documenting rather than an
accident of exception hierarchy, and future sibling-site work (e.g.
distinguishing shutdown-cancel from transport-cancel) has an obvious
hook. Behavior on pre-3.8 Pythons where CancelledError WAS an Exception
subclass is also corrected: the old path would have caught it and
treated it as a connection failure worth retrying.
Closes#9930.
PR #21238 introduced top-level `allOf: [{if/then/required}]` blocks in the
built-in memory tool's parameters schema as conditional-required hints.
Two problems:
1. OpenAI's Codex backend (chatgpt.com/backend-api/codex, gpt-5.x) rejects
top-level `allOf`/`anyOf`/`oneOf`/`enum`/`not` outright with a
non-retryable 400 — affected every user on openai-codex/gpt-5.x.
2. The `if/then` hints were silently ignored by every other provider
(Chat Completions doesn't honour them on function schemas), so they
never actually enforced anything anywhere.
The runtime handler in `memory_tool()` already validates the per-action
required fields and returns actionable error messages, so removing the
block changes nothing behaviourally.
Paired with the defense-in-depth sanitizer in the previous commit, this
closes the bug both at the source (schema no longer emits the forbidden
form) and at the wire boundary (sanitizer strips it if anything else
re-introduces it).
- Rewrites `tests/tools/test_memory_tool_schema.py` to guard against
regressing the forbidden-combinator shape instead of asserting it.
- Adds AUTHOR_MAP entry for @hrkzogw (author of the sanitizer fix).
Mirrors the Slack `allowed_channels` feature (PR #7401) and Discord's
`allowed_channels` (PR #7044) across the remaining group-capable platforms.
All five platforms (Slack + Discord + the four added here) now follow the
same pattern: primary config via config.yaml, env-var fallback as an escape
hatch — matching the project policy that .env is for secrets only and
behavioral settings belong in config.yaml.
Also fixes a duplicate `slack` key in DEFAULT_CONFIG introduced by PR
#7401 (the later entry silently overwrote `allowed_channels`, `require_mention`,
and `free_response_channels` at dict-literal evaluation time).
Platforms added:
- Telegram: `telegram.allowed_chats` (env alias: `TELEGRAM_ALLOWED_CHATS`)
- Mattermost: `mattermost.allowed_channels` (env alias: `MATTERMOST_ALLOWED_CHANNELS`)
- Matrix: `matrix.allowed_rooms` (env alias: `MATRIX_ALLOWED_ROOMS`)
- DingTalk: `dingtalk.allowed_chats` (env alias: `DINGTALK_ALLOWED_CHATS`)
Mattermost and Matrix previously had NO config.yaml bridging for any of
their gating settings; this PR adds `load_gateway_config` bridges for them
(Mattermost gets require_mention + free_response_channels + allowed_channels;
Matrix gets allowed_rooms on top of its existing bridges for require_mention
and free_response_rooms).
Semantics identical everywhere:
- Empty = no restriction (fully backward compatible).
- Non-empty = hard whitelist: non-listed chats are silently ignored,
even when the bot is @mentioned.
- DMs bypass the check entirely.
DEFAULT_CONFIG merges the duplicate `slack` block and adds new `mattermost`
and `matrix` blocks so all gating settings surface in defaults.
Not included: Feishu (has its own per-chat `chat_rules` system that covers
this use case differently), WhatsApp (already has `group_allow_from` via
`group_policy: allowlist`), pure-DM platforms (Signal, SMS, BlueBubbles,
Yuanbao — no group concept).
Self-chat mode (default) previously replied to ANY incoming DM with a
Python-side pairing-code message. Two compounding defaults:
1. allowlist.js::matchesAllowedUser returned true for an empty
allowlist — so WHATSAPP_ALLOWED_USERS unset → everyone passes the JS
bridge gate → messages reach Python gateway → _is_user_authorized
returns False but _get_unauthorized_dm_behavior falls back to
'pair' → stranger gets a pairing code reply.
2. bridge.js had no mode check on !fromMe messages, so self-chat mode
(where the operator only wants to talk to themselves) forwarded
everything anyway.
Fix:
- allowlist.js: empty allowlist now returns false. Operators who want
an open bot must set WHATSAPP_ALLOWED_USERS=* explicitly (the
existing wildcard behaviour, consistent with SIGNAL_GROUP_ALLOWED_USERS).
- bridge.js: self-chat mode hard-rejects all !fromMe messages at the
bridge, before they ever reach the Python gateway. Bot mode still
enforces the allowlist.
- Startup log message updated to reflect the new per-mode behaviour
(was '⚠️ No WHATSAPP_ALLOWED_USERS set — all messages will be
processed', which was both inaccurate post-fix and a bad default
signal pre-fix).
- allowlist.test.mjs: new regression test pinning the empty-rejects
contract, + null/undefined defensive cases.
Behaviour delta for existing users:
- self-chat mode, no allowlist: strangers got pairing codes, now
silently dropped. Strictly better.
- bot mode, no allowlist: strangers got pairing codes via the
Python-side pairing flow, now silently dropped at the JS bridge.
Operators who genuinely want an open bot set
WHATSAPP_ALLOWED_USERS=*.
The original #21086 report was theme-accent opaque fills behind JSON
payload values in the Kanban Task Drawer's EVENTS section. The first
iteration of this fix was narrow — add ``!important`` to the specific
drawer/payload overrides. But "all themes" includes user-installable
themes we haven't written yet, and any theme doing the normal
``code { background: ... !important }`` dance would break this again.
Replace the whack-a-mole approach with a structural reset:
1. Inside ``.hermes-kanban`` (and the ``.hermes-kanban-drawer`` portal
container), reset EVERY ``<code>`` and ``<pre>`` to transparent
with ``!important``. This is the new default.
2. Opt back in ONLY on the classes that carry intentional pill
styling:
- ``.hermes-kanban .hermes-kanban-md code`` (inline code in task
Markdown body) — ``:not()`` scoped to exclude fenced blocks.
- ``.hermes-kanban pre.hermes-kanban-md-code`` (fenced block
wrapper) — higher specificity than the reset so it wins cleanly.
Net effect: any theme — shipped or third-party — can ship whatever
global ``code``/``pre`` rule it wants; kanban surfaces stay clean
unless the theme deliberately targets our internal class names, which
would be a conscious override rather than an accidental breakage.
Verified live against a hostile synthetic theme that paints
``code``, ``pre``, AND ``.hermes-kanban code`` / ``.hermes-kanban pre``
with ``background: !important`` fills. Every kanban surface stayed
correct (transparent where expected, intentional pill fill where
expected). Also verified across all 7 shipped themes by pointing a
headless browser at a live dashboard.
| Surface | Expected | Got |
|----------------------------------------------------|--------------------|-------------------|
| Outside ``.hermes-kanban`` (sanity) | hostile fill | hostile fill ✓ |
| Drawer ``.hermes-kanban-event-payload`` (the bug) | transparent | transparent ✓ |
| Drawer bare ``<code>`` | transparent | transparent ✓ |
| Drawer bare ``<pre>`` | transparent | transparent ✓ |
| Markdown inline ``<code>`` | subtle pill | subtle pill ✓ |
| Markdown fenced block ``.hermes-kanban-md-code`` | subtle pill | subtle pill ✓ |
| Markdown fenced inner ``<code>`` | transparent | transparent ✓ |
Closes#21086.
When the parent agent uses a composite toolset like hermes-cli, calling
delegate_task with individual toolsets (e.g. web, terminal) resulted in
zero tools because the name-based intersection failed: 'web' != 'hermes-cli'.
Add _expand_parent_toolsets() which collects all tool names from parent
toolsets, then recognises any individual toolset whose tools are a subset
of the parent's available tools. This allows delegate_task(toolsets=['web'])
to work correctly when the parent has hermes-cli enabled.
Fixes#19447
The Hermes dashboard previously assumed it was served at the root of its
host (e.g. https://kanban.tilos.com/). When mounted behind a path-prefix
reverse proxy (e.g. https://mission-control.tilos.com/hermes/), the SPA
404'd because:
- index.html shipped absolute /assets/index-*.js URLs
- React Router had no basename
- The plugin loader hit /dashboard-plugins/<name>/... at the root host
- CSS in the bundle had absolute url(/fonts/...) references
This patch makes the dashboard prefix-aware at runtime, no rebuild
required. The proxy injects 'X-Forwarded-Prefix: /hermes' on every
request and the Python server:
- Rewrites href/src in served index.html to '${prefix}/assets/...'
- Injects 'window.__HERMES_BASE_PATH__="${prefix}"' for the SPA to read
- Rewrites url() refs in CSS at serve time
The SPA reads window.__HERMES_BASE_PATH__ once at boot and:
- Prefixes all /api/... fetches via api.ts
- Prefixes all /dashboard-plugins/... script/css URLs in usePlugins
- Sets <BrowserRouter basename={...}> so client-side routing works
When no X-Forwarded-Prefix header is present, behavior is unchanged
(empty prefix => serves at root, kanban.tilos.com keeps working).
Refs: MC-AUTO-13
Add tencent/hy3-preview (without :free suffix) as a paid model route
alongside the existing free variant. This allows seamless transition
when the model moves from free to paid on OpenRouter — both routes
coexist so neither side's timing causes breakage.
Changes:
- models.py: add ("tencent/hy3-preview", "") to OPENROUTER_MODELS
- model-catalog.json: add paid variant entry
- tests: add assertions for paid route presence
The :free entry can be removed in a follow-up PR once OpenRouter
confirms the free route is deprecated.
Co-authored-by: simonweng <simonweng@tencent.com>
Some exception classes (e.g. anyio.ClosedResourceError) are raised without
a message argument, so str(exc) returns an empty string. The existing error
format f'{type(exc).__name__}: {exc}' would produce messages like
'MCP call failed: ClosedResourceError: ' with nothing after the colon.
Add _exc_str() helper that falls back to repr(exc) when str(exc) is empty,
and apply it to all 6 MCP error formatting sites (5 tool/prompt/resource
handlers + 1 sampling handler).
Fixes#19417
Treat closed-resource, closed-transport, broken-pipe, and EOF MCP failures as stale session equivalents so the existing reconnect/retry-once path can recover. Add regression coverage for the stale-pipe marker variants.\n\nChecks:\n- python -m py_compile tools/mcp_tool.py tests/tools/test_mcp_tool_session_expired.py\n- python -m pytest tests/tools/test_mcp_tool_session_expired.py -q -o addopts=\n- selected secret scan over touched files
The alibaba-coding-plan provider (DashScope coding-intl endpoint) was
defined in providers.py but missing from _PROVIDER_MODELS in models.py.
This caused /model to show "0 models" for this provider even though
credentials were configured and the provider was functional.
Add the curated model list so the provider picker displays available
models correctly.
Extracts the three try/write_runtime_status/except-log blocks into a
shared _write_runtime_status_safe() helper. On failure, logs the first
occurrence per (platform, context) at warning level and downgrades
subsequent failures to debug — so a persistently broken status dir
(permissions, ENOSPC) doesn't spam the log on every Telegram reconnect.
Uses getattr for the _status_write_logged set so test harnesses that
skip __init__ (object.__new__(Adapter)) don't break.
Follow-up to the salvaged #21158.
Track elapsed wall time in _run_on_mcp_loop, cancel the in-flight future when a timeout expires, and raise a descriptive TimeoutError that includes the elapsed and configured timeout. Add regression coverage for the new timeout diagnostics.
