Multi-turn transcripts ran together visually because every user message
got the same vertical rhythm regardless of position. Adds a short ─── in
the border colour above every user message after the first, so each turn
reads as its own block. Height estimator gains a `withSeparator` flag so
virtual scrolling pre-allocates the extra two rows (rule + top margin)
and avoids a jump on first measurement.
While in the area: the busy-indicator duration was padded with
`padStart(7)`, leaving five visible spaces between `·` and the digits
(`⠋ · 2s`) — especially loud under the verb-less `unicode` style.
Drop the padding entirely (`⠋ · 2s`); the model label now shifts a few
columns as the duration grows, which is the right trade-off for the
minimal indicator styles. The verb-padding test stays; the
duration-padding test is removed alongside the function it covered.
The quick setup flow (recommended for first-time users) silently defaulted
terminal.backend to 'local' without ever presenting the choice. This meant
new users who wanted Docker, SSH, Modal, Daytona, or any other backend had
to know about 'hermes setup terminal' — which most wouldn't discover until
later.
Now the quick setup flow is:
1. Provider selection
2. API key
3. Terminal backend (local/Docker/Modal/SSH/Daytona/Vercel/Singularity)
4. Messaging platform
5. Done
The terminal backend is a foundational decision (where ALL commands run)
and belongs in the onboarding path alongside provider selection.
Small follow-ups on top of #19643:
- check_auth() takes quiet kwarg to suppress its AUTHENTICATED print
when called from check_auth_live(), so the final status line reflects
the live-call outcome only.
- Drop redundant _ensure_deps() call in check_auth_live() (check_auth()
already calls it).
- Add AUTHOR_MAP entry for ygd58 so release attribution script works.
setup.py --check only validated token shape/expiry but did not detect
when Google had disabled the OAuth client or account. Users got
AUTHENTICATED even when actual API calls failed with disabled_client.
Changes:
- Catch disabled_client and invalid_client in check_auth() refresh
path with actionable guidance (check Cloud Console, check account
status, do not retry)
- Add check_auth_live() that performs a real Calendar API call to
detect disabled_client errors that survive token refresh
- Add --check-live CLI flag backed by check_auth_live()
Fixes#19570
Adds one reserved token to the cron `deliver` field:
- `all` — expand to every platform with a configured home channel
Resolves at fire time, not create time, so a job created before Telegram
was wired up picks it up once `TELEGRAM_HOME_CHANNEL` is set. Composes
with existing targets: `origin,all`, `all,telegram:-100:17`.
Inspired by Vellum Assistant's reminder routing-intent system.
## Changes
- cron/scheduler.py: _expand_routing_tokens + integrate into _resolve_delivery_targets
- tools/cronjob_tools.py: schema description updated
- tests/cron/test_scheduler.py: TestRoutingIntents (5 cases)
- website/docs/user-guide/features/cron.md: docs + table rows
## Validation
- tests/cron/test_scheduler.py -k 'Routing or Deliver' → 57 passed
The previous revision of this PR added six GMI-specific branches
(`elif base_url_host_matches(..., 'api.gmi-serving.com')`) across
run_agent.py and agent/auxiliary_client.py, plus a _HERMES_UA_HEADERS
constant in auxiliary_client.py.
ProviderProfile already has a `default_headers: dict[str, str]` field
commented as 'Client-level quirks (set once at client construction)'.
Other plugins (ai-gateway, kimi-coding) already use it. Two of the four
auxiliary_client sites we previously patched already had a generic
`else: profile.default_headers` fallback that picked it up (so did
both run_agent sites).
This revision:
* Sets `default_headers={'User-Agent': 'HermesAgent/<ver>'}` on the
GMI profile in plugins/model-providers/gmi/__init__.py.
* Reverts all six GMI-specific branches in run_agent.py and
auxiliary_client.py.
* Adds the generic profile-fallback `else` block to the two
auxiliary_client sites (`_to_async_client`, `resolve_provider_client`)
that didn't have it yet. This benefits every provider whose profile
declares default_headers, not just GMI — e.g. Vercel AI Gateway's
HTTP-Referer/X-Title now flow through the async client path too.
* Replaces the GMI-specific URL-branch tests with a profile-level
assertion and keeps the run_agent integration test (with
`provider='gmi'` so the fallback picks up the profile).
Net diff vs main: +82/-0 across 5 files, touching only the GMI plugin,
two generic fallback blocks in auxiliary_client.py, AUTHOR_MAP, and
tests. No core files change.
Based on #20907 by @isaachuangGMICLOUD.
When switching from a custom local provider (e.g. ollama-launch) to a
cloud provider, two bugs caused the CLI to misbehave:
1. _explicit_api_key/_explicit_base_url were only updated when the switch
result had non-empty values (guarded by `if result.api_key:` etc.).
If the previous provider set these to Ollama values ("ollama",
"http://127.0.0.1:11434/v1"), those stale values leaked into the next
turn's _ensure_runtime_credentials() call and were forwarded to the
new provider's API endpoint, causing authentication/routing failures.
Fix: unconditionally write result.api_key/base_url into the explicit
fields after every successful switch. An empty string is the correct
sentinel — it tells _ensure_runtime_credentials to re-resolve from the
auth store / config rather than forwarding a stale override.
2. In AIAgent.switch_model(), `self.base_url = base_url or self.base_url`
kept the old Ollama localhost URL whenever the incoming base_url was an
empty string. For providers that use a native SDK (not an OpenAI-compat
endpoint), the caller passes base_url="" and expects the agent to clear
the field — not silently inherit Ollama's address.
Fix: only update self.base_url when base_url is truthy.
3. _handle_model_picker_selection() was called from the prompt_toolkit
Enter key binding without any exception guard. Any unexpected error
in the model-selection code path propagated through prompt_toolkit's
key-binding dispatcher and caused the entire TUI to exit — which the
user sees as "the terminal exits when I switch providers".
Fix: wrap the call in try/except and close the picker on failure.
Weak judge models (e.g. deepseek-v4-flash) return empty strings or prose
when asked for the strict {done, reason} JSON verdict. The old code
failed-open to continue on every such turn, burning the entire turn
budget with log lines like
judge returned empty response
judge reply was not JSON: "Let me analyze whether the goal..."
and /goal clear could not stop it mid-loop without /stop.
After N=3 consecutive *parse* failures (transport/API errors don't
count — those are transient), the loop auto-pauses and prints:
⏸ Goal paused — the judge model (3 turns) isn't returning the
required JSON verdict. Route the judge to a stricter model in
~/.hermes/config.yaml:
auxiliary:
goal_judge:
provider: openrouter
model: google/gemini-3-flash-preview
Then /goal resume to continue.
The counter resets on any usable reply (both "done"/"continue" and
API errors) and persists across GoalManager reloads so cross-session
resumes carry the correct state.
Also fixes test_goal_verdict_send.py sharing a hardcoded session_id
across tests — the shared id only worked because the previous
_post_turn_goal_continuation was a never-awaited coroutine. Now that
PR #19160 made it properly awaited, the xdist test-leakage bug
surfaced. Each test gets a unique session_id via uuid suffix.
Route goal status notices through the platform adapter send API and register post-delivery callbacks so completed-goal notices appear after the final assistant response. Also cancel queued synthetic goal continuations on /goal pause and /goal clear while preserving normal queued user messages.
Makes first-time use of the kanban view self-explanatory. Every control
that wasn't already labelled now has a `title` tooltip describing what
it does, and a `?` icon next to the board switcher opens the kanban
docs page in a new tab.
Coverage:
- BoardSwitcher: board select, + New board button, docs-link icon
(both compact and full variants)
- BoardToolbar: Search, Tenant, Assignee, Show archived, Nudge
dispatcher, Refresh
- BulkActionBar: → ready, Complete, Archive, reassign group, Apply,
Clear
- Column header: hovering the header now surfaces COLUMN_HELP as a
tooltip in addition to the visible sub-text; column count also
labelled
- Card: task id, priority badge, tenant badge, assignee/unassigned,
comment count, link count, age timestamp
- InlineCreate: assignee, priority, parent-task selectors
Closes the community feedback from @CharlieDePew asking for tooltips
and a docs link in the kanban view.
Relevant docs page:
https://hermes-agent.nousresearch.com/docs/user-guide/features/kanban
When the installer is run via , uv resolves config file
paths against the process owner's (root) home directory rather than the
effective user's, causing a Permission denied error when trying to read
/root/uv.toml.
Setting UV_NO_CONFIG=1 prevents uv from discovering any config files
(uv.toml, pyproject.toml) during installation, which is the correct
behavior for a bootstrap script that manages its own environment.
Fixes#21269
channels_list was iterating directory.items() directly, yielding
("updated_at", str) and ("platforms", dict) pairs — neither passed
the isinstance(entries_list, list) check, so the inner loop never ran
and every call returned count=0 even when channel_directory.json was
populated.
The writer (gateway/channel_directory.py) wraps the payload as
{"updated_at": ..., "platforms": {...}}; every other reader in the
codebase unwraps via directory.get("platforms", {}). This aligns
channels_list with that convention.
Also tightens the existing test_channels_with_directory test, which
bypassed the bug by asserting against _load_channel_directory() directly
instead of calling channels_list. It now calls the tool end-to-end and
a new test_channels_with_directory_platform_filter covers the filter
path. Both tests fail against the pre-fix code.
Closes#21474
Co-authored-by: chrisworksai <262485129+chrisworksai@users.noreply.github.com>
- Add pricing entries for Claude Opus 4.5/4.6/4.7, Sonnet 4.5/4.6, and
Haiku 4.5 with updated source URLs (platform.claude.com)
- Add _normalize_anthropic_model_name() to handle dot-notation variants
(e.g. claude-opus-4.7 → claude-opus-4-7) for pricing lookups
- Fix silent token loss: ensure session row exists before UPDATE in both
run_agent.py and hermes_state.py (INSERT OR IGNORE is idempotent)
- Log token persistence failures at DEBUG level instead of swallowing
them silently — makes undercounted analytics diagnosable
- Surface reasoning tokens in CLI /usage and TUI usage panel
- Add 'reasoning' and 'cost_status' fields to TUI Usage type
The kanban specifier landed in #21435 with feature-page docs (the
kanban page itself + the CLI reference table), but three other docs
pages enumerate every auxiliary task slot and were missed:
user-guide/configuration.md Auxiliary Models section —
interactive picker example
+ full auxiliary config
reference YAML block.
user-guide/features/fallback-providers.md
Both 'Auxiliary Tasks' and
'Fallback Reference' tables.
user-guide/features/kanban-tutorial.md
Triage-column bullet now
mentions the ✨ Specify
button + CLI + slash command.
No other docs enumerate the aux task slots (verified with
grep -r 'title_generation\|auxiliary.session_search' website/docs/).
The existing mapping pointed to the wrong GitHub user (blakejohnson, id
866695, IBM) — the email actually belongs to voteblake (id 5585957),
confirmed via search/commits?author-email. Mis-credited since 323ca7084.
* feat(kanban): add `specify` — auxiliary LLM fleshes out triage tasks
The Triage column shipped with a placeholder 'a specifier will flesh
out the spec', but the specifier itself was never built. This wires
it up as a dedicated CLI verb.
`hermes kanban specify <id>` calls the auxiliary LLM (configured under
`auxiliary.triage_specifier`) to expand a rough one-liner into a
concrete spec — tightened title plus a body with Goal / Approach /
Acceptance criteria / Out-of-scope sections — then atomically flips
`status: triage -> todo` and recomputes ready so parent-free tasks
go straight to the dispatcher on the same tick.
Surface:
hermes kanban specify <task_id> # single task
hermes kanban specify --all [--tenant T] # sweep triage column
hermes kanban specify ... --author NAME # audit-comment author
hermes kanban specify ... --json # one JSON line per task
Design choices:
- Parent gating is preserved. specify_triage_task flips to 'todo',
then recompute_ready promotes to 'ready' only when parents are
done — same rule as a normal parent-gated todo.
- No daemon, no background watcher. Every invocation is explicit —
keeps cost predictable and doesn't fight the dispatcher loop.
- Response parse is lenient: strict JSON preferred, markdown-fence
tolerated, raw-body fallback on malformed JSON so the LLM can't
strand a task in triage.
- All failure modes (no aux client, API error, task moved out of
triage mid-call) return SpecifyOutcome(ok=False, reason=...) so
--all continues past individual failures.
Changes:
hermes_cli/kanban_db.py + specify_triage_task()
hermes_cli/kanban_specify.py NEW (~220 LOC — prompt, parse, call)
hermes_cli/kanban.py + specify subcommand + _cmd_specify
hermes_cli/config.py + auxiliary.triage_specifier task slot
website/docs/user-guide/features/kanban.md specify + config notes
website/docs/reference/cli-commands.md CLI reference entry
tests/hermes_cli/test_kanban_specify_db.py NEW (10 tests)
tests/hermes_cli/test_kanban_specify.py NEW (20 tests)
Validation: 30/30 targeted tests pass. E2E: triage task -> specify ->
ends in 'ready' with events [created, specified, promoted] and the
audit comment recorded under the configured author.
* feat(kanban): wire specifier into dashboard and gateway slash
Follow-ups to the initial PR #21435 — closes the two gaps I'd left as
post-merge: dashboard button and first-class gateway surface.
Dashboard (plugins/kanban/dashboard/)
- POST /tasks/:id/specify NEW endpoint. Thin wrapper around
kanban_specify.specify_task(). Returns the CLI outcome shape
({ok, task_id, reason, new_title}); ok=false with a human reason
is a 200, not a 4xx, so the UI can render it inline without
treating 'no aux client configured' as a crash.
- Runs sync in FastAPI's threadpool because the LLM call can take
tens of seconds on reasoning models.
- Pins HERMES_KANBAN_BOARD around the specify call so the module's
argless kb.connect() lands on the right board.
- dist/index.js: doSpecify callback threaded through the drawer →
TaskDetail → StatusActions prop chain. ✨ Specify button appears
ONLY when task.status === 'triage' (elsewhere the backend would
reject anyway — hide the button to keep the action row clean).
Busy state (Specifying…) + inline success/error banner under the
button using the response.reason text.
- dist/style.css: tiny hermes-kanban-msg-ok / -err classes using
existing --color vars so themes reskin cleanly.
Gateway slash (/kanban specify)
- Already works via the existing run_slash → build_parser →
kanban_command pipeline. No code change needed — slash commands
inherit the argparse tree automatically. Added coverage:
test_run_slash_specify_end_to_end (create --triage, specify, verify
promotion + retitle) and test_run_slash_specify_help_is_reachable.
Tests
- tests/plugins/test_kanban_dashboard_plugin.py: 3 new tests for the
REST endpoint — happy path, non-triage rejection as ok=false 200,
missing aux client as ok=false 200.
- tests/hermes_cli/test_kanban_cli.py: 2 new slash-surface tests.
Docs
- website/docs/user-guide/features/kanban.md: dashboard action row
description mentions ✨ Specify + all three surfaces. REST table
gains /tasks/:id/specify. Slash examples include /kanban specify.
Validation: 340/340 targeted tests pass. E2E via TestClient: create a
triage task over REST → POST /specify with mocked aux client → task
moves to 'ready' column on /board with new title and body applied.
Both implement WebSearchProvider via tools/web_providers/ — matching the
existing SearXNG pattern (PR #5c906d702). Search-only; pair with any
extract provider via web.extract_backend.
- tools/web_providers/brave_free.py — Brave Search API (free tier, 2k
queries/mo). Uses BRAVE_SEARCH_API_KEY as X-Subscription-Token.
- tools/web_providers/ddgs.py — DuckDuckGo via the ddgs Python package.
No API key; gated on package importability.
- tools/web_tools.py: both backends added to _get_backend() config list
and auto-detect chain (trails paid providers), _is_backend_available,
web_search_tool dispatch, web_extract_tool + web_crawl_tool search-only
refusals, check_web_api_key, and the __main__ diagnostic. Introduces
_ddgs_package_importable() helper so tests can monkeypatch a single
symbol for the ddgs availability check.
- hermes_cli/tools_config.py: picker entries for both providers; ddgs
gets a post_setup handler that runs `pip install ddgs`.
- hermes_cli/config.py: BRAVE_SEARCH_API_KEY in OPTIONAL_ENV_VARS.
- scripts/release.py: AUTHOR_MAP entry for @Abd0r.
- tests: 14 new tests (brave-free) + 15 new tests (ddgs) covering
provider unit behavior, backend wiring, and search-only refusals.
Salvages the brave-free + ddgs portion of PR #19796. Not included: the
in-line helpers in web_tools.py (replaced with provider modules to match
the shipped architecture), the lynx-based extract path (these backends
should refuse extract with a clear error — users pair with a real
extract provider), and scripts/start-llama-server.sh (unrelated).
Co-authored-by: Abd0r <223003280+Abd0r@users.noreply.github.com>
Extends PR #21400's resource inlining with image-specific handling: ACP
resource_link and embedded blob resources with an image/* mime (or image
file suffix when mime is missing) now emit an OpenAI image_url part
with a base64 data URL, so vision models actually see the image
instead of a [Binary file omitted] note. Non-image resources keep the
existing text-inlining behavior.
Adds 3 tests: local PNG via resource_link, JPEG mime inferred from
suffix when client omits mimeType, and embedded blob PNG.
The May 5 refactor in d5357f816 made _message_thread_id_for_typing()
symmetric with _message_thread_id_for_send() by mapping the General
topic (thread id "1") to None upfront for both. That's correct for
sendMessage — Telegram rejects message_thread_id=1 on sends and the
topic must be omitted — but it's wrong for sendChatAction.
Observed behavior (confirmed via before/after Telegram wire traces):
Before d5357f816: thread_id=1 → message_thread_id=1 → bubble visible in General
After d5357f816: thread_id=1 → message_thread_id=None → no visible typing
Omitting message_thread_id on sendChatAction does NOT fall back to
the General topic's view in a forum-enabled supergroup; the bubble
ends up hidden from the client's General-topic pane entirely. For
any user on a forum-group, the typing indicator stopped appearing.
Fix: drop the symmetric "1 → None" mapping from the typing resolver.
sendMessage still maps 1 → None via _message_thread_id_for_send (that
side was never broken). The asymmetry is real and required by
Telegram's API — document it in the resolver docstring.
Partial revert of d5357f816; restores the behavior from 0cf7d570e
("fix(telegram): restore typing indicator and thread routing for
forum General topic"). Does not re-introduce the retry-without-thread
fallback that 41545f7ec scoped down for DM topics — with the resolver
fixed, the first call already hits the right wire shape.
Test updated from test_send_typing_general_topic_uses_none_thread_id
(which encoded the broken contract) to
test_send_typing_preserves_general_topic_thread_id, asserting the
single correct call with message_thread_id=1. 10 other tests in the
file untouched and passing.
When empty-response terminal scaffolding fires on a tool-result turn,
_drop_trailing_empty_response_scaffolding left the live history ending at
a bare 'tool' message. The next user input then landed as [...tool, user],
a protocol-invalid sequence that OpenRouter/Opus and other providers
silently fail on (returns empty content). That retriggered the empty-retry
recovery every turn, and recovery flags never hit SQLite (no column for
them), so history kept looking broken on every reload.
Two fixes:
1. Scaffolding strip rewinds the orphan assistant(tool_calls)+tool pair
after popping sentinels. Only fires when scaffolding flags were
actually present, so mid-iteration tool loops are untouched.
2. _repair_message_sequence runs right before every API call as a
defensive belt: drops stray tool messages with unknown tool_call_ids,
merges consecutive user messages so no user input is lost. Does NOT
rewind assistant(tool_calls)+tool+user — that pattern is valid when
the user redirected before the model got its continuation turn.
Repro: session 20260507_044111_fa7e65. Opus-4.7/OpenRouter returned
content-less response after a 42KB execute_code output, nudge+retry
chain exhausted (no fallback configured), terminal sentinel appended,
scaffolding stripped leaving bare tool tail, user typed 'wtf happened..'
and landed as tool→user violation. Every subsequent turn collapsed in
<50ms with the same 3-retry empty chain because the API request itself
was malformed.
Verified live via HTTP mock: pre-fix reproduced 5 api_calls/0.15s exit
'empty_response_exhausted'; post-fix 1 api_call/0.10s exit
'text_response(finish_reason=stop)'. Three-turn session flows cleanly
through the scenario. Full run_agent suite: 1242 passed (0 regressions,
2 pre-existing concurrent_interrupt failures unrelated).
cmd_update's auto-restart path could leave the gateway dead after a
transient failure in systemd's own auto-restart window. Reproduced
on Ubuntu 25.10 + systemd 257: after update, gateway drains and exits 75,
systemd's first respawn 60s later fails (status=200/CHDIR with
"No such file or directory" on a WorkingDirectory that demonstrably
exists), the unit ends up in RestartMaxDelaySec=300 backoff, and
cmd_update's fallback 'systemctl restart' never recovers it — leaving
users with a permanently silent gateway until they manually run
'systemctl reset-failed'.
The fix mirrors the recovery pattern 'hermes gateway restart'
(systemd_restart) got in PR #20949: always reset-failed before
restart, on both the initial fallback and the retry. Also rewrites
the final failure message to tell the user to reset-failed +
restart (not just restart, which is the step that already failed
twice).
cron/scheduler.py:run_job() constructed AIAgent(...) without ever calling
discover_mcp_tools(). The CLI and gateway paths do this at startup; cron
jobs inherited none of it and the user's configured mcp_servers were
invisible inside every cron run.
Insert discover_mcp_tools() right before AIAgent(), wrapped in try/except
so a broken MCP server can't kill an otherwise-working cron job. The call
is idempotent: register_mcp_servers() short-circuits on already-connected
servers, so subsequent ticks in the same scheduler process pay ~0ms.
Scoped to the LLM path only; no_agent script jobs skip it entirely.
Closes#4219.
Makes the in-tree QQ inline keyboards actually light up when the agent
blocks on a dangerous-command approval. Matches the cross-adapter
gateway contract already implemented by Discord, Telegram, Slack,
Matrix, and Feishu.
Gateway/run.py's _approval_notify_sync checks type(adapter).send_exec_approval
and falls back to a text prompt when it's missing. Without this wiring,
QQ users stared at plain '/approve' text even though the adapter shipped
button primitives.
### send_exec_approval(chat_id, command, session_key, description, metadata)
Matches the signature the gateway calls with. Builds an ApprovalRequest
(command_preview, description, timeout) and delegates to send_approval_request.
Uses the last inbound msg_id as reply_to so QQ accepts the passive
message. The 'metadata' parameter is accepted for contract parity but
intentionally unused — QQ doesn't have thread_id/DM-targeting overrides.
### send_update_prompt(chat_id, prompt, default, session_key, metadata)
Signature updated to match the cross-adapter contract used by
'hermes update --gateway' watcher. Renders a 'Update Needs Your Input'
prompt with the optional default hint and a Yes/No keyboard. Replaces
the earlier 3-arg helper that wasn't wired anywhere.
### Default interaction dispatcher
_default_interaction_dispatch() auto-registered as the adapter's
interaction callback in __init__. Routes:
- approve:<session_key>:<decision> → tools.approval.resolve_gateway_approval
Button → choice mapping:
allow-once → 'once'
allow-always → 'always'
deny → 'deny'
(QQ's 3-button mobile layout deliberately collapses 'session' + 'always'
into one button; /approve session text fallback remains available.)
- update_prompt:<answer> → atomic write of y/n to ~/.hermes/.update_response
(the detached 'hermes update --gateway' watcher polls this file)
- anything else → logged and dropped
Resolve exceptions are caught and logged — never propagate into the WS
loop. Callers can override via set_interaction_callback() to route
clicks elsewhere or pass None to drop them entirely.
### Net effect
QQ users now get native tap-to-approve UX on dangerous-command prompts
and update-confirmation prompts, without having to type /approve or /deny
as text. The adapter hooks into tools.approval the same way every other
button-capable platform does.
### Tests
14 new tests cover:
- Default callback installed on __init__
- send_exec_approval / send_update_prompt exist as class methods (so the
gateway's type-probe detects them)
- allow-once/always/deny each map to the correct resolve choice
- update_prompt:y / update_prompt:n each write atomically to the response
file (via monkeypatched get_hermes_home)
- Unknown button_data / empty button_data / resolve exceptions are harmless
- send_exec_approval honours last_msg_id reply-to and accepts metadata
- send_update_prompt delegates with correct content + keyboard
Full qqbot suite: 144 passed (72 pre-existing + 72 from this salvage arc).
Also ran tools/test_approval.py alongside — no regressions (276 passed
combined).
Co-authored-by: WideLee <limkuan24@gmail.com>
_scan_cron_prompt ran at cron create/update time on the user-supplied
prompt but skill content loaded inside _build_job_prompt at runtime
was never scanned. Combined with non-interactive auto-approval, a
malicious skill carrying an injection payload could execute with full
tool access every tick.
- cron/scheduler.py: new CronPromptInjectionBlocked exception and
_scan_assembled_cron_prompt helper. _build_job_prompt now routes
both return paths (with skills / without skills) through the helper,
raising on match. run_job catches the exception and returns a clean
(False, blocked_doc, "", error) tuple so the operator sees a BLOCKED
delivery with the scanner result and an audit hint, rather than a
scheduler crash or a silent skip.
- tests/cron/test_cron_prompt_injection_skill.py: 10 regression tests.
Unit coverage on _scan_assembled_cron_prompt (clean/injection/exfil/
invisible-unicode). End-to-end coverage via _build_job_prompt with
planted skills (injection payload, env exfil, zero-width space,
clean control, missing-skill-doesn't-crash). Fixture patches
tools.skills_tool.SKILLS_DIR / HERMES_HOME so planted skills are
visible. Importantly uses the current cron.scheduler module object
(not a top-level import) so tests don't break when other fixtures
reload cron.scheduler — CronPromptInjectionBlocked identity depends
on which module object defined it.
For every connected MCP server we register four "utility" tool schemas
(mcp_<server>_list_resources, read_resource, list_prompts, get_prompt).
The existing gate was `hasattr(server.session, method)` — but
`mcp.ClientSession` defines all four methods on the class regardless of
what the remote server supports, so the gate never filtered anything.
Tools-only servers (e.g. @upstash/context7-mcp which advertises only
`tools`) ended up with 4 dead stubs; every model call to them returned
JSON-RPC -32601 Method not found, which made the model conclude the
server was broken even when the real tools worked.
Capture the `InitializeResult` returned by `await session.initialize()`
on the `MCPServerTask`, then gate each utility schema on the
corresponding `capabilities` sub-object (resources / prompts). A
legacy `hasattr` fallback runs when `initialize_result` is missing
(older test fixtures / not-yet-captured code paths) so pre-existing
behavior is preserved.
Verified against real `mcp.types.InitializeResult` pydantic models:
- Context7 shape (tools only) → 0 utility stubs registered (was 4)
- Resources-only server → 2 stubs (list_resources, read_resource)
- Prompts-only server → 2 stubs (list_prompts, get_prompt)
- Fully capable server → all 4 stubs
Closes#18051.
Co-authored-by: nikolay-bratanov <nikolay-bratanov@users.noreply.github.com>
Follow-up to the previous commit:
- Add _is_loopback_host() helper covering 127.0.0.1, localhost, ::1,
ip6-localhost, ip6-loopback (case-insensitive). Empty/None host is
treated as non-loopback since unset usually means public default bind.
- Fix mixed-indent comment in the safety rail (comment now aligned with
the if-block) and collapse the nested-if into one condition.
- Add TestInsecureNoAuthSafetyRail covering rejection on 0.0.0.0, a LAN
IP, and empty host; allowance on 127.0.0.1/localhost; plus unit-level
parametrized coverage of _is_loopback_host for spellings we can't bind
in the hermetic test env (::1, ip6-localhost, ip6-loopback).
- Pin test_connect_starts_server + test_webhook_deliver_only defaults
to 127.0.0.1 so they keep passing under the new rail.
- Document the behavior in website/docs/user-guide/messaging/webhooks.md.
