Generic 400 and server-disconnect heuristics used absolute token/message-count fallbacks that are too aggressive for 1M context sessions. Gate those absolute fallbacks to smaller context windows while preserving relative pressure checks.
Fixes#16351
Reverts ff3d2773e2. Teknium reviewed the merged PR and decided this
behavior isn't wanted — tool-driven kanban_create should not mirror
the slash-command path's auto-subscribe. Orchestrators that want
their originating chat notified can call kanban_notify-subscribe
explicitly; we're not going to make it implicit.
Closes#19479.
When an orchestrator agent calls kanban_create from a gateway session
(e.g. a Telegram user delegating to an orchestrator profile), auto-
subscribe the originating (platform, chat, thread, user) to the new
task's terminal events. Mirrors the behavior of the /kanban create
slash command in gateway/run.py so tool-driven creation is at parity
with human-driven creation.
Without this, a user who interacts with an orchestrator exclusively
via the gateway never receives blocked / completed / gave_up
notifications for tasks the orchestrator created on their behalf —
silently breaking the gateway-first multi-agent flow the reporter
describes.
Reads the context-local HERMES_SESSION_* vars via get_session_env()
(not os.environ — those are contextvars for asyncio concurrency
safety). Falls through cleanly in CLI / cron contexts with no
session active (subscribed=False in the response). Best-effort: if
the gateway module isn't importable (test rigs stubbing gateway.*),
the task still creates, we just skip the subscription.
Response gains a 'subscribed' bool so the orchestrator knows whether
terminal events will land back in the originating chat or whether it
needs to poll / unblock manually.
Tests: 4 new in tests/tools/test_kanban_tools.py covering
CLI/no-subscribe, telegram/gateway-auto-subscribe, discord-DM/no-
thread subscribe, and partial-ctx/no-chat_id no-subscribe. 40/40
kanban tool tests pass.
Open-weight models (DeepSeek, Qwen, GLM) sometimes emit tool calls like
`{"urls": "https://a.com"}` when the tool schema declares
`type: array`. The call was JSON-valid but semantically wrong, and
`coerce_tool_args` would pass the bare string through — the tool then
failed with a confusing type error.
`coerce_tool_args` now wraps non-list, non-null values in a
single-element list when the schema declares `array`. Strings still go
through `_coerce_value` first so JSON-encoded arrays
(`'["a","b"]'`) parse correctly and nullable `"null"` still
becomes `None`. `None` itself is preserved — tools with sensible
defaults already handle it, and we don't want to silently mask a
deliberate null.
Salvaged from #19652 (NikolayGusev-astra) — the broader validate-then-
repair layer had several issues (duplicated existing coercion,
mis-classified `old_string` as a path field, prepended non-JSON
prefixes to tool results that break downstream JSON parsing, hardcoded
offset/limit defaults unsuitable for non-read_file tools). The one
genuinely new capability is wrapping bare scalars, which is implemented
here directly inside the existing coercion path.
Co-authored-by: Nikolay Gusev <ngusev@astralinux.ru>
Mirrors the Codex auto-import UX. On successful Nous login (either
`hermes auth add nous --type oauth` or `hermes login nous`), tokens are
mirrored to `$HERMES_SHARED_AUTH_DIR/nous_auth.json` (default
`~/.hermes/shared/nous_auth.json`, outside any named profile's
HERMES_HOME). On next login in a new profile, the flow offers to import
those credentials ("Import these credentials? [Y/n]") and rehydrates via
a forced refresh+mint instead of running the full device-code flow.
Runtime refresh in any profile syncs the rotated refresh_token back to
the shared store so sibling profiles don't hit stale-token fallback
after rotation.
The volatile 24h agent_key is NOT persisted to the shared store —
only the long-lived OAuth tokens are cross-profile useful.
- `HERMES_SHARED_AUTH_DIR` env var for tests + custom layouts
- Pytest seat belt mirrors the existing `_auth_file_path` guard so
forgetting to redirect the store in a test fails loudly
- File mode 0600 where platform supports it
- Runtime credential resolution is unchanged — shared store is only
consulted during the login flow, so profile isolation at runtime is
preserved
- Stale refresh_token + portal-down cases gracefully fall back to
device-code
Addresses a user report from Mike Nguyen: running
`hermes --profile <name> auth add nous --type oauth` for every new
profile is unnecessary friction now that Codex has a shared-import
flow via `~/.codex/auth.json`.
Closes#19534 (security).
A worker spawned by the kanban dispatcher has HERMES_KANBAN_TASK set
to its own task id. The destructive tools (kanban_complete,
kanban_block, kanban_heartbeat) resolved task_id via
_default_task_id() which preferred an explicit arg over the env var,
with no ownership check — so a buggy or prompt-injected worker could
complete / block / heartbeat any OTHER task (sibling, cross-tenant,
anything) by supplying its id. Reporter's repro: worker for t_A
passed task_id=t_B to kanban_complete and got {"ok": true}.
Fix: add _enforce_worker_task_ownership(tid). If HERMES_KANBAN_TASK
is set and tid doesn't match, return a structured tool error with
guidance to use kanban_comment (for information handoff across tasks)
or kanban_create (for follow-up work). Orchestrator profiles (no env
var, but kanban toolset enabled per #18968) are exempt — their job
is routing and sometimes includes closing out child tasks.
Kept unrestricted (deliberately):
- kanban_show — workers legitimately read parent/sibling handoff context
- kanban_comment — cross-task comments are the handoff mechanism
- kanban_create — orchestrator fan-out, worker follow-up spawning
- kanban_link — parent/child linking
Tests: 5 new regression tests in tests/tools/test_kanban_tools.py
covering the grid (worker-attacks-foreign ×3 tools, worker-own-task
preserved, orchestrator-unrestricted). 36/36 pass.
Instead of an unhelpful CalledProcessError traceback when running
`hermes gateway start/stop/restart` without first installing the service,
check for the unit file and exit with an actionable install hint.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Reporter of #19535 explicitly asked for a regression test — covers it
here so a future refactor of _set_status_direct can't silently re-enable
the direct ready/todo -> running bypass.
Asserts both: (a) HTTP 400 with 'running' in the detail message, and
(b) the task's status is unchanged after the rejected PATCH (pre-request
status preserved, no partial mutation).
The test 'test_inf_stays_string_for_integer_only' incorrectly asserted
that _coerce_number('inf') returns float('inf'), but the function
correctly returns the original string 'inf' because infinity is not
JSON-serializable.
Fixed the assertion to expect the string 'inf', and added two new tests
for negative infinity and NaN edge cases to improve coverage of the
non-JSON-serializable number guard in _coerce_number().
Follow-up to @changchun989's cherry-pick: reverts the validate-via-
normalize change so validate_profile_name remains a strict regex check
on the input AS-GIVEN. Callers that accept mixed-case user input
(dashboard UI, CLI args, import flows) call normalize_profile_name()
first, then validate the result. This keeps validate honest about
what the on-disk directory name must look like — e.g. ' jules '
(trailing whitespace) is now rejected instead of silently trimmed
and accepted.
- validate_profile_name: strict lowercase/regex check again, 'UPPER'
back in the invalid-names parametrize
- 8 call sites in profiles.py (create_profile, delete_profile,
set_active_profile, export_profile, import_profile, rename_profile,
resolve_profile_env, plus the clone_from branch): swap the
normalize-then-validate order
- scripts/release.py: add changchun989@proton.me -> changchun989 to
AUTHOR_MAP so CI doesn't block on the unmapped contributor email
All kanban + profile tests pass (268 across test_profiles.py +
test_kanban_db.py + test_kanban_core_functionality.py, plus 73 in
test_kanban_tools.py + test_kanban_dashboard_plugin.py).
Closes#18498.
- Add normalize_profile_name() for lowercase canonical IDs and Default alias
- Use canonical names in create/delete/rename/export/import/set_active paths
- Canonicalize Kanban assignee on create/assign, list filter, and worker spawn
- Tests for mixed-case assignees and profile resolution (fixes#18498)
`hermes import` was creating secret files with the process umask
(typically 0644) instead of 0600. zipfile.open() does not honor the
Unix mode bits stored in zip member external_attr; the restore loop
used open(target, "wb") which always falls back to umask.
Threat: silent privilege downgrade after a routine restore on
multi-user systems (shared dev boxes, CI runners, jump hosts) — any
local user could read API keys and OAuth tokens from ~/.hermes/.
Fix mirrors the convention already used at file creation
(hermes_cli/auth.py: stat.S_IRUSR | stat.S_IWUSR for auth.json).
The quick-snapshot restore path (restore_quick_snapshot) is
unaffected — it uses shutil.copy2 which preserves perms via
copystat().
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds first-class board support to kanban so users can separate unrelated
streams of work (projects, repos, domains) into isolated queues. Single-
project users stay on the 'default' board and see no UI change.
Isolation model
---------------
- Each board is a directory at `~/.hermes/kanban/boards/<slug>/` with
its own `kanban.db`, `workspaces/`, and `logs/`. The 'default' board
keeps its legacy path (`~/.hermes/kanban.db`) for back-compat — fresh
installs and pre-boards users get zero migration.
- Workers spawned by the dispatcher have `HERMES_KANBAN_BOARD` pinned in
their env alongside the existing `HERMES_KANBAN_DB` /
`HERMES_KANBAN_WORKSPACES_ROOT` pins, so workers physically cannot see
other boards' tasks.
- The gateway's single dispatcher loop now sweeps every board per tick;
per-tick cost is a few extra filesystem stats.
- CAS concurrency guarantees are preserved per-board (each board is its
own SQLite DB, same WAL+IMMEDIATE machinery as before).
CLI
---
hermes kanban boards list|create|switch|show|rename|rm
hermes kanban --board <slug> <any-subcommand>
Board resolution order: `--board` flag → `HERMES_KANBAN_BOARD` env →
`~/.hermes/kanban/current` file → `default`. Slug validation is strict:
lowercase alphanumerics + hyphens + underscores, 1-64 chars, starts with
alphanumeric. Uppercase is auto-downcased; slashes / dots / `..` /
control chars are rejected so boards can't name their way out of the
boards/ directory.
Passive discoverability: when more than one board exists, `hermes kanban
list` prints a one-line header ("Board: foo (2 other boards …)") so
users who stumble across multi-project never have to hunt for the
feature. Invisible for single-board installs.
Dashboard
---------
- New `BoardSwitcher` component at the top of the Kanban tab: dropdown
with all boards + task counts, `+ New board` button, `Archive`
button (non-default only). Hidden entirely when only `default` exists
and is empty — single-project users never see it.
- New `NewBoardDialog` modal: slug / display name / description / icon
+ "switch to this board after creating" checkbox.
- Selected board persists to `localStorage` so browser users don't
shift the CLI's active board out from under a terminal they left open.
- New `?board=<slug>` query param on every existing endpoint plus a
new `/boards` CRUD surface (`GET /boards`, `POST /boards`,
`PATCH /boards/<slug>`, `DELETE /boards/<slug>`,
`POST /boards/<slug>/switch`).
- Events WebSocket is pinned to a board at connection time; switching
opens a fresh WS against the new board.
Also fixes a pre-existing bug in the plugin's tenant / assignee
filters: the SDK's `Select` uses `onValueChange(value)`, not
native `onChange(event)`, so those filters silently didn't work.
New `selectChangeHandler` helper wires both signatures.
Tests
-----
49 new tests in `tests/hermes_cli/test_kanban_boards.py` covering:
slug validation (valid / invalid / auto-downcase), path resolution
(default = legacy path, named = `boards/<slug>/`, env var override),
current-board resolution chain (env > file > default), board CRUD +
archive / hard-delete, per-board connection isolation (tasks don't
leak), worker spawn env injection (`HERMES_KANBAN_BOARD`,
`HERMES_KANBAN_DB`, `HERMES_KANBAN_WORKSPACES_ROOT` all point at the
right board), and end-to-end CLI surface.
Regression surface: all 264 pre-existing kanban tests continue to pass.
Live-tested via the dashboard: created 3 boards (default,
hermes-agent, atm10-server), created tasks on each via both CLI
(`--board <slug> create`) and dashboard (inline create on the Ready
column), confirmed zero cross-board leakage, confirmed `BoardSwitcher`
+ `NewBoardDialog` work end-to-end in the browser.
AnyUrl was imported inside the same try block as mcp.client.auth, so
when the mcp package was not installed, AnyUrl was undefined and
_build_client_metadata raised NameError at runtime.
Moved the AnyUrl import to its own try/except block so it's available
whenever pydantic is installed (which is a core dependency), regardless
of whether the mcp SDK is present.
Also added pytest.importorskip('mcp') to the three
test_build_client_metadata tests that exercise _build_client_metadata,
since that function depends on OAuthClientMetadata from the mcp package.
Six tests in test_bedrock_adapter.py import botocore.exceptions
directly (ConnectionClosedError, EndpointConnectionError,
ReadTimeoutError, ClientError) without guarding the import. When
botocore is not installed (it's an optional dependency), these tests
fail with ModuleNotFoundError instead of being gracefully skipped.
Added pytest.importorskip('botocore') to each affected test function,
following the same pattern used elsewhere in the test suite (e.g.
test_voice_mode.py for numpy, test_mcp_oauth.py for mcp).
Tests affected:
- TestIsStaleConnectionError: 3 tests
- TestCallConverseInvalidatesOnStaleError: 3 tests
Before: 6 FAIL with ModuleNotFoundError
After: 6 SKIP with reason message
TestTranscribeLocalExtended patches faster_whisper.WhisperModel, which
triggers an ImportError when the faster_whisper package is not installed.
Added a pytest.mark.skipif marker using importlib.util.find_spec so
these tests are gracefully skipped instead of failing with
ModuleNotFoundError.
The resilient restart settings from PR #18639 only took effect when
the gateway was started via `hermes gateway start` or `hermes gateway
restart` — both of which call refresh_systemd_unit_if_needed() which
writes the new unit and runs daemon-reload.
However, when the gateway self-restarts via exit-code-75 (stale-code
detection after `hermes update`, or the /restart command), systemd
respawns the process directly without going through any CLI function.
The unit file on disk stays stale, and systemd keeps using the old
cached settings (StartLimitBurst=5, RestartSec=30) until someone
manually runs `hermes gateway restart`.
This meant that after PR #18639 was deployed, users who never ran
`hermes gateway restart` manually were still vulnerable to the
permanent-death-on-network-outage bug.
Fix: call refresh_systemd_unit_if_needed() at the top of run_gateway()
(the foreground entry point that systemd's ExecStart invokes). This
ensures that on every boot — whether triggered by systemd restart,
exit-75 respawn, or manual foreground run — the unit definition and
daemon state are current. The call is best-effort (exceptions caught)
and a no-op when the unit is already current (one stat + string compare).
Set max_result_size_chars=100_000 on the read_file registry entry (was
float('inf')), closing the Layer 2 defense-in-depth gap in
tool_result_storage.py. The existing Layer 1 guard inside
_handle_read_file already returns a JSON error for oversized reads;
this aligns the registry cap with every other tool.
Update test_read_file_never_persisted → test_read_file_result_size_cap
to assert 100_000, and add test_read_file_registry_cap_is_100k as an
explicit regression guard against re-introducing float('inf').
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The contributor's PR silently swallowed ValueError from
SessionDB.set_session_title() with bare except Exception: pass.
Users typing /new <title> with an already-in-use title got an
untitled session and no feedback.
Changes:
- cli.py: catch ValueError from both sanitize_title() and
set_session_title(); print the error and mark the session
untitled in the banner (never echo the rejected title back).
- gateway/run.py: append a warning note to the reset reply on
title rejection; reflect the accepted title in the header.
- Add regression tests for the duplicate-title path in CLI and
gateway.
Also map exx@example.com -> @exxmen in scripts/release.py.
Allow users to start a fresh session and immediately set its title by
passing a name to /new (or /reset):
/new Refactor auth module
Changes:
- hermes_cli/commands.py: add args_hint='[name]' to /new command
- cli.py: parse title argument in process_command(), pass to new_session()
- cli.py: new_session() accepts title=None, sets title via SessionDB
- gateway/run.py: _handle_reset_command() parses title, sets on new entry
- gateway/session.py: reset_session() accepts optional display_name
- tests: add test_new_session_with_title, test_reset_command_with_title,
test_new_command_in_help_output
All 36 affected tests pass.
Treat explicit CDP override mode as a valid browser backend even when agent-browser is absent, and add a regression test to prevent false-negative availability gating.
The 'q' alias is defined for 'queue' command in commands.py:93.
The hardcoded 'q' in cli.py:5910 was dead code - resolve_command('q')
returns the queue CommandDef, so canonical would never be 'q'.
Removes the misleading check without changing any behavior:
- /quit and /exit still exit (defined aliases)
- /q still maps to queue (as intended)
Tighten the provenance semantics added in #19618: skills a user asks a
foreground agent to write via skill_manage(create) now stay invisible to
the curator. Only skills the background self-improvement review fork
sediments through skill_manage get the created_by=agent marker.
- tools/skill_provenance.py — new ContextVar module mirroring the
_approval_session_key pattern: set_current_write_origin / reset /
get / is_background_review. Default origin is 'foreground'; the
review fork sets 'background_review'.
- run_agent.py — run_conversation() binds the ContextVar from
self._memory_write_origin at the top of each call. The review fork
runs on its own thread (fresh context), so foreground and review
contexts never cross-contaminate.
- tools/skill_manager_tool.py — skill_manage(action='create') now
only calls mark_agent_created() when is_background_review(). All
other cases (foreground create, patch, edit, write_file, delete)
continue as before.
- tests: test_skill_provenance.py (6 tests covering the ContextVar
surface), split test_full_create_via_dispatcher into foreground
vs. review-fork variants, curator status tests now mark-first.
Why: the agent routinely edits existing user skills on the user's
behalf; those writes must never flip provenance. And when a user
explicitly asks the foreground agent to create a skill, that skill
belongs to the user. The curator should only be cleaning up after
its own autonomous sediment from the review nudge loop.
_reconfigure_provider() updates cloud_provider/backend/tts.provider when
switching tool providers via "hermes setup tools → Reconfigure", but did
not update the matching use_gateway flag. _configure_provider() (the
initial-setup path) sets use_gateway on all three tool categories. The
omission in _reconfigure_provider leaves a stale value in config.yaml:
switching from a Nous-managed provider (use_gateway=True) to a self-hosted
one keeps use_gateway=True, continuing to route requests through the Nous
gateway; switching the other way leaves use_gateway unset so the managed
feature does not activate.
Fix: mirror _configure_provider's use_gateway = bool(managed_feature)
assignment in the tts, browser, and web blocks of _reconfigure_provider.
Symmetric across all three tool categories. No behavior change for any
provider that does not set tts_provider, browser_provider, or web_backend.
Fixes#15229
PR #19427 dropped the 'You are a Kanban worker' identity line from
KANBAN_GUIDANCE so SOUL.md stays authoritative for profile identity.
This test assertion was stale against that change; update it to the
new protocol-only header.
_build_child_agent constructed child AIAgents without passing
fallback_model, leaving _fallback_chain=[] for every subagent.
When a subagent hit a rate-limit or credential exhaustion the
runtime fallback check (run_agent.py:7486 / 12267) found an empty
chain and failed immediately — even though the parent agent was
configured with fallback_providers and would have recovered.
The cron scheduler already propagates fallback_model correctly
(scheduler.py:1038). Fix closes the parity gap by reading the
parent's _fallback_chain (the normalised list form accepted by
AIAgent's fallback_model parameter) and threading it through.
Empty chains coerce to None so AIAgent initialises _fallback_chain=[]
as usual rather than iterating an empty list.
Preflight compression can run synchronously before the first model call when a loaded session exceeds the active context threshold. Gateway users saw no visible progress while the compression LLM call was in flight, which can look like a dropped message during long compactions.\n\nEmit the existing lifecycle status through _emit_status before starting preflight compression so CLI, gateway, and WebUI status callbacks all get immediate feedback.\n\nAdds a regression assertion for the preflight path.
Follow-up to #19586 (@cixuuz salvage): _get_ancestor_pids walks ps -o ppid=
up the process tree, which the pre-existing mock in
test_find_gateway_pids_falls_back_to_pid_file_when_process_scan_fails didn't
expect. Return empty stdout so the ancestor loop terminates cleanly and the
original fallback assertion still passes.
Quick commands of type "alias" that target built-in slash commands
(e.g. /h -> /model) were processed too late in _handle_message — after
the if-canonical=="model" checks. This meant alias expansion never
reached the target handler and fell through to the LLM as raw text.
Two fixes:
1. Move the quick_commands block before built-in dispatch so alias
targets (like /model) hit the correct handler after expansion.
2. Extract bare command name from target_command via .split()[0] to
feed _resolve_cmd() correctly (was using the full arg-string).
_setup_slack() was the only platform setup function that did not prompt
for a home channel. All four sibling setups (_setup_telegram,
_setup_discord, _setup_mattermost, _setup_bluebubbles) close with an
identical home-channel block, and setup_gateway() already checks for
SLACK_HOME_CHANNEL presence at the end of the wizard — but the value
was never collected, leaving cron delivery and cross-platform
notifications silently broken for Slack after a fresh hermes setup run.
Add the standard home-channel prompt at the end of _setup_slack(),
symmetric with the Discord implementation. Add two unit tests that
verify the prompt is saved when provided and skipped when left blank.
Adds four regression tests guarding the bugfix in the previous commit:
- TestGetDueJobs::test_broken_cron_without_next_run_is_recovered exercises
cron schedules whose next_run_at was lost; expects compute_next_run to
repopulate it within get_due_jobs() rather than silently skipping the job.
- TestGetDueJobs::test_broken_interval_without_next_run_is_recovered does
the same for interval schedules.
- TestResolveOrigin::test_string_origin_is_tolerated and
test_non_dict_origin_is_tolerated confirm _resolve_origin() returns None
for legacy/hand-edited origins (string, list, int) instead of raising.
Co-Authored-By: Claude <noreply@anthropic.com>
Follow-up on #9925 cherry-pick adding two additional tests:
- bytes content hashes identically to its str-decoded form
- mixed bytes+str bundle hash equals the on-disk content_hash from
skills_guard (the production invariant used to detect drift)
Also map dodofun@126.com and 1615063567@qq.com in AUTHOR_MAP so the
CI contributor check passes for the cherry-picked commit.
Co-authored-by: LeonSGP43 <cine.dreamer.one@gmail.com>
Co-authored-by: zhao0112 <1615063567@qq.com>
_classify_removed_skills used naive 'in' substring matching to detect
whether a removed skill's name appeared in skill_manage arguments.
Short/common skill names (api, git, test, foo, etc.) matched
incorrectly when they appeared as substrings of longer words in file
paths (references/api-design.md) or content (latest, testing).
Replace with field-aware matching:
- file_path: needle must match a complete filename stem or directory
name, with -/_ normalised for variant tolerance
- content fields: word-boundary regex (\b) prevents embedding in
longer words
Also add 3 regression tests covering the false-positive scenarios.
list_profiles_on_disk() hardcodes Path.home() / ".hermes" / "profiles",
ignoring HERMES_HOME when set to a custom root (e.g. /opt/data).
Add test_list_profiles_on_disk_custom_root to cover this case.
Related to #18442, #18985.
The old CWD heuristic was fooled by:
1. TERMINAL_CWD persisted to .env by `hermes config set terminal.cwd`
2. Inherited TERMINAL_CWD from parent hermes processes
3. Only resolved when config had a placeholder value (not explicit paths)
Fix:
- load_cli_config() unconditionally uses os.getcwd() for local backend
- TERMINAL_CWD always force-exported in CLI mode (overrides stale values)
- Gateway sets _HERMES_GATEWAY=1 marker so lazy cli.py imports don't clobber
- Remove terminal.cwd from config-set .env sync map (prevents re-poisoning)
- Clarify setup wizard label as 'Gateway working directory'
Closes#19214
`_tui_need_npm_install()` compares the canonical `package-lock.json` against
the hidden `node_modules/.package-lock.json` to decide whether `npm install`
needs to re-run. npm 9 drops the `"peer": true` field from the hidden lock
on dev-deps that are *also* declared as peers (the canonical lock preserves
the dual annotation). That made the check flag 16 packages (`@babel/core`,
`@types/node`, `@types/react`, `@typescript-eslint/*`, `react`, `vite`,
`tsx`, `typescript`, …) as mismatched on every launch, triggering a runtime
`npm install`.
Inside the Docker image, that runtime install then fails with EACCES because
`/opt/hermes/ui-tui/node_modules/` is root-owned from build time, so
`docker run … hermes-agent --tui` prints:
Installing TUI dependencies…
npm install failed.
…and exits 1, with no preview. The empty preview is a second bug: the
launcher captured only stderr, but npm 9 writes EACCES to stdout, which
was DEVNULL'd.
Fixes:
- Add `"peer"` to `_NPM_LOCK_RUNTIME_KEYS` so the comparison ignores the
non-deterministic field, alongside the existing `"ideallyInert"`.
- Capture stdout as well as stderr in the install subprocess so future
failures surface a useful preview instead of a bare "failed." line.
Regression tests:
- `test_no_install_when_only_peer_annotation_differs` — the exact scenario
- `test_install_when_version_differs_even_with_peer_drop` — guards against
the peer-drop tolerance masking a real version skew
On-host impact: the same false-positive was firing on every `hermes --tui`
invocation from a normal checkout, silently running a no-op `npm install`
each time (it converged because the host's `node_modules/` is writable).
Startup time on the TUI should drop noticeably.
Cron jobs that reference skills via their skills: config never bumped
the usage counters in .usage.json, so the curator could auto-archive
skills actively used by cron jobs based on stale timestamps.
Now _build_job_prompt() calls bump_use(skill_name) for each
successfully loaded skill so the curator sees them as active.
_try_anthropic() lacked the explicit_api_key parameter added to
_try_openrouter() in #18768. When resolve_provider_client() is called
with provider="anthropic" and an explicit key (e.g. from a fallback_model
entry with api_key set), the key was silently ignored — _try_anthropic()
always fell back to resolve_anthropic_token(), so the fallback returned
None,None for users without a default Anthropic credential configured.
Fix: add explicit_api_key: str = None to _try_anthropic() and use
explicit_api_key or <pool/env fallback> in both the pool-present and
no-pool paths. Pass explicit_api_key=explicit_api_key at the call site
in resolve_provider_client(). Symmetric with the _try_openrouter() fix.
No behavior change when explicit_api_key is None.
Users commonly place `require_mention: true` at the top level of
config.yaml alongside `group_sessions_per_user`, expecting it to gate
Telegram group messages. The key was silently ignored because the
config loader only checked `yaml_cfg["telegram"]["require_mention"]`.
When `require_mention` is found at the top level and no telegram-specific
value is set, the fix now:
- adds it to platforms_data["telegram"]["extra"] so _telegram_require_mention()
picks it up via the primary config.extra path
- sets TELEGRAM_REQUIRE_MENTION env var for the secondary fallback path
A telegram-specific value (telegram.require_mention) still takes
precedence over the top-level shorthand.
Also corrects telegram.md: bare /cmd without @botname is rejected when
require_mention is enabled; only /cmd@botname (bot-menu form) passes.
Fixes#3979
Deduplicate exact and near-exact Discord voice STT transcripts per guild/user over a short window to avoid duplicate delayed agent replies.
Adds regression tests for exact and near-duplicate voice transcript suppression.
Curator review fork now forwards per-slot credentials from auxiliary.curator
and legacy curator.auxiliary to resolve_runtime_provider, matching the
canonical aux task schema. Add regression tests for binding and main fallback.
Layers defense-in-depth on top of the shared-root anchoring (base commit).
Changes in hermes_cli/kanban_db.py:
- kanban_db_path() now honours HERMES_KANBAN_DB first, then falls through
to kanban_home()/kanban.db.
- workspaces_root() now honours HERMES_KANBAN_WORKSPACES_ROOT first, then
falls through to kanban_home()/kanban/workspaces.
- All three overrides (HERMES_KANBAN_HOME, HERMES_KANBAN_DB,
HERMES_KANBAN_WORKSPACES_ROOT) now call .expanduser() for consistency.
- _default_spawn() injects HERMES_KANBAN_DB and
HERMES_KANBAN_WORKSPACES_ROOT into the worker subprocess env. Even
when the worker's get_default_hermes_root() resolution somehow
disagrees with the dispatcher's (symlinks, unusual Docker layouts),
the two processes still open the same SQLite file.
Module docstring updated to describe all three overrides and the
dispatcher env-injection contract.
Tests (tests/hermes_cli/test_kanban_db.py, TestSharedBoardPaths):
- test_hermes_kanban_db_pin_beats_kanban_home
- test_hermes_kanban_workspaces_root_pin_beats_kanban_home
- test_empty_per_path_overrides_fall_through
- test_dispatcher_spawn_injects_kanban_db_and_workspaces_root
(monkeypatches subprocess.Popen, asserts both env vars reach the
child even after HERMES_HOME is rewritten by `hermes -p <profile>`.)
Docs: website/docs/reference/environment-variables.md gets entries
for the three kanban env vars.
This fusion is built on the cleanest of the seven competing PRs that
targeted issue #18442:
* Base commit (from PR #19350 by @GodsBoy): add `kanban_home()` helper
anchored at `get_default_hermes_root()`, reroute all 5 kanban path
sites through it (including the 3 sibling log-dir sites that the
other six PRs missed), 8-test regression class.
* Dispatcher env-var injection approach drawn from PRs #18300
(@quocanh261997) and #19100 (@cg2aigc).
* Per-path env overrides drawn from PR #19100 (@cg2aigc).
* get_default_hermes_root() resolution direction first proposed in
PR #18503 (@beibi9966) and PR #18985 (@Gosuj).
Closes the duplicate/competing PRs: #18300, #18503, #18670, #18985,
#19037, #19056, #19100. Fixes#18442 and #19348.
Co-authored-by: quocanh261997 <17986614+quocanh261997@users.noreply.github.com>
Co-authored-by: cg2aigc <232694053+cg2aigc@users.noreply.github.com>
Co-authored-by: beibi9966 <beibei1988@proton.me>
Co-authored-by: Gosuj <123411271+Gosuj@users.noreply.github.com>
Co-authored-by: LeonSGP43 <154585401+LeonSGP43@users.noreply.github.com>
The Kanban board is documented as shared across all Hermes profiles, but
`kanban_db_path()` and `workspaces_root()` resolved through `get_hermes_home()`,
which returns the active profile's HERMES_HOME. When the dispatcher spawned a
worker with `hermes -p <profile> --skills kanban-worker chat -q "work kanban
task <id>"`, the worker rewrote HERMES_HOME to the profile subdirectory before
kanban_db.py imported, opening a profile-local `kanban.db` that did not contain
the dispatcher's task. `kanban_show` and `kanban_complete` failed; the
dispatcher's row stayed `running` and was retried/crashed. The same defect
applied to `_default_spawn`'s log directory and `worker_log_path`, so
`hermes kanban tail` did not see the worker's output.
Add `kanban_home()` in `hermes_cli/kanban_db.py` that resolves through
`HERMES_KANBAN_HOME` (explicit override) then `get_default_hermes_root()`,
which already understands the `<root>/profiles/<name>` and Docker / custom
HERMES_HOME shapes. Reroute `kanban_db_path`, `workspaces_root`, the
`_default_spawn` log directory, `gc_worker_logs`, and `worker_log_path`
through it. Profile-specific config, `.env`, memory, and sessions stay
isolated as before; only the kanban surface is shared.
Add a `TestSharedBoardPaths` regression class to `tests/hermes_cli/test_kanban_db.py`
covering: default install, profile-worker convergence, Docker custom HERMES_HOME,
Docker profile layout, explicit `HERMES_KANBAN_HOME` override, and a real
SQLite round-trip across dispatcher and worker HERMES_HOME perspectives.
The dispatcher/worker convergence tests fail on origin/main and pass after
the fix.
Update the `kanban.md` user-guide page and the misleading docstrings in
`kanban_db.py` to describe the shared-root behavior.
Fixes#19348
CLI/TUI sessions on the local backend now unconditionally use
os.getcwd() as the working directory. The terminal.cwd config value is
only consumed by gateway/cron/delegation modes (where there's no shell
to cd from).
Previously, 'hermes setup' would write an absolute path (e.g. $HOME)
into terminal.cwd which then pinned the CLI to that directory regardless
of where the user launched hermes from. This was a silent foot-gun —
the user's 'cd' was being ignored.
Changes:
1. cli.py: Restructured CWD resolution — if TERMINAL_CWD is not already
set by the gateway, and the backend is local, always use os.getcwd().
Config terminal.cwd is irrelevant for interactive CLI/TUI sessions.
2. setup.py: Moved the cwd prompt from setup_terminal_backend() to
setup_gateway(). It now only appears when configuring messaging
platforms and is labeled 'Gateway working directory'.
3. Tests: Rewrote test_cwd_env_respect.py to validate the new behavior:
explicit config paths are ignored for CLI, gateway pre-set values are
preserved, non-local backends keep their config paths.
4. Docs: Updated configuration.md, profiles.md, and
environment-variables.md to clarify that terminal.cwd only affects
gateway/cron mode on local backend.
Closes#19214
Apply agent.redact.redact_sensitive_text with force=True to log content
captured by _capture_log_snapshot before it reaches upload_to_pastebin.
On-disk logs are untouched. Compatible with the off-by-default local
redaction policy from #16794: this is upload-time-only and applies
regardless of security.redact_secrets because the public paste service
is the leak surface. A visible banner is prepended to each uploaded log
paste so reviewers know redaction was applied. --no-redact preserves
deliberate unredacted sharing for maintainer-coordinated cases.
The bug-report, setup-help, and feature-request issue templates direct
users to run hermes debug share and paste the resulting public URLs.
With redaction off by default per #16794, those uploads have been
carrying credentials onto paste.rs and dpaste.com.
force=True is non-negotiable: without it, redact_sensitive_text
short-circuits at agent/redact.py:322 when the env var is unset, so the
fix would silently be a no-op for its target audience. A regression
test pins this down.
Fixes#19316
* feat: add video_analyze tool for native video understanding
Adds a video_analyze tool that sends video files to multimodal LLMs
(e.g. Gemini) for analysis via the OpenRouter-compatible video_url
content type. Mirrors vision_analyze in structure, error handling,
and registration pattern.
Key design:
- Base64 encodes entire video (no frame extraction, no ffmpeg dep)
- Uses 'video_url' content block type (OpenRouter standard)
- Supports mp4, webm, mov, avi, mkv, mpeg formats
- 50 MB hard cap, 20 MB warning threshold
- 180s minimum timeout (videos take longer than images)
- AUXILIARY_VIDEO_MODEL env override, falls back to AUXILIARY_VISION_MODEL
- Same SSRF protection, retry logic, and cleanup as vision_analyze
Default disabled: registered in 'video' toolset (not in _HERMES_CORE_TOOLS).
Users opt in via: hermes tools enable video, or enabled_toolsets=['video'].
* feat(video): add models.dev capability pre-check + CONFIGURABLE_TOOLSETS entry
- Pre-checks model video capability via models.dev modalities.input
before expensive base64 encoding. Fails early with helpful message
suggesting video-capable alternatives (gemini, mimo-v2.5-pro).
- Passes optimistically if model unknown or lookup fails.
- Adds ModelInfo.supports_video_input() helper.
- Adds 'video' to CONFIGURABLE_TOOLSETS and _DEFAULT_OFF_TOOLSETS
so 'hermes tools enable video' works from CLI.
- 8 new tests for the capability check (37 total).
* refactor(video): remove models.dev capability pre-check
Removes _check_video_model_capability and ModelInfo.supports_video_input.
The vision_analyze tool doesn't pre-check image capability either — both
tools rely on the same pattern: send request, handle API errors gracefully
with categorized user-facing messages. The pre-check was inconsistent
(only worked for some providers/models) so drop it for parity.
* cleanup: compress comments, fix fragile timeout coupling
- Replace _VISION_DOWNLOAD_TIMEOUT * 2 with hardcoded 60s (no silent
breakage if vision timeout changes independently)
- Strip verbose comments and redundant log lines throughout
- No behavioral changes
Under context pressure, frontier models sometimes emit tool calls with
required fields dropped. Previously _handle_write_file() used
args.get('content', '') which substituted an empty string for the missing
key, returned success with bytes_written=0, and created a zero-byte file
on disk. The model had no way to detect the failure.
Changes:
- Reject calls where 'path' is absent or not a non-empty string
- Reject calls where 'content' key is entirely absent (key-presence check,
not truthiness) — distinguishing a legitimately empty file from a dropped arg
- Reject calls where 'content' is a non-string type
- All error messages include guidance to re-emit the tool call or switch
to execute_code with hermes_tools.write_file() for large payloads
- Explicit empty string content (file truncation) continues to work
Regression tests added for all four cases: missing path, missing content,
explicit-empty content, and wrong content type.
Fixes#19096
``_resolve_origin`` called ``origin.get('platform')`` on whatever
``job.get('origin')`` returned. The leading ``if not origin: return None``
short-circuited the falsy cases (None, empty dict, "") but a non-empty
string passed that guard and then crashed with
``AttributeError: 'str' object has no attribute 'get'`` on every fire
attempt. Observed in the wild after a migration script tagged jobs with
free-form provenance strings (e.g.
``"combined-digest-replaces-x-and-y-20260503"``).
``mark_job_run`` did record ``last_status: error,
last_error: "'str' object has no attribute 'get'"`` once, but the next
tick re-loaded the same poisoned origin and crashed identically. The
job stayed enabled, fired every tick, and accumulated cascading errors
in the log until ``origin`` was patched manually.
Replace the falsy guard with ``isinstance(origin, dict)``. Non-dict
origins (string, int, list, tuple, float — anything that survived a
hand-edit, JSON-script write, or migration) are now treated the same
as a missing origin: the job continues with ``deliver`` falling back
through its normal home-channel path instead of crashing the scheduler
loop.
Test parametrises the non-dict shapes that can appear in jobs.json
through external writers and asserts ``_resolve_origin`` returns None
for each.
Note: this fix scope is the non-dict-``origin`` crash only. The
``next_run_at: null`` recurring-job recovery (the second sub-bug in
#18722) is independently addressed by the in-flight #18825, which
extends the never-silently-disable defense from #16265 to
``get_due_jobs()`` — that approach is well-aligned with the existing
recovery pattern and ships fine without a competing change here.
Fixes#18722 (non-dict origin crash; recurring-job recovery covered by #18825)
/goal was silently broken outside the classic CLI.
TUI: /goal was routed through the HermesCLI slash-worker subprocess,
which set the goal row in SessionDB but then called
_pending_input.put(state.goal) — the subprocess has no reader for that
queue, so the kickoff message was discarded. No post-turn judge was
wired into prompt.submit either, so even a manual kickoff would not
continue the goal loop. Intercept /goal in command.dispatch instead,
drive GoalManager directly, and return {type: send, notice, message}
so the TUI client renders the Goal-set notice and fires the kickoff.
Run the judge in _run_prompt_submit after message.complete, surface
the verdict via status.update {kind: goal}, and chain the continuation
turn after the running guard is released.
Gateway: _post_turn_goal_continuation was gated on
hasattr(adapter, 'send_message'), but adapters only expose send().
That branch was dead on every platform — users never saw
'✓ Goal achieved', 'Continuing toward goal', or budget-exhausted
messages. Replace the dead call with adapter.send(chat_id, content,
metadata) and drop a broken reference to self._loop.
Tests:
- tests/tui_gateway/test_goal_command.py — full /goal dispatch matrix
(set / status / pause / resume / clear / stop / done / whitespace)
plus regressions for slash.exec → 4018 and 'goal' staying in
_PENDING_INPUT_COMMANDS.
- tests/gateway/test_goal_verdict_send.py — locks in the adapter.send
path for done / continue / budget-exhausted and verifies the hook
no-ops when no goal is set or the adapter lacks send().
SlackAdapter.connect() overwrote self._handler, self._app, and
self._socket_mode_task without closing the prior AsyncSocketModeHandler
first. If connect() was called a second time on the same adapter (e.g.
during a gateway restart or in-process reconnect attempt), the old Socket
Mode websocket stayed alive. Both the old and new connections received
every Slack event and dispatched it twice — producing double responses
with different wording, the same bug that affected DiscordAdapter (#18187,
fixed in #18758).
Fix: add a close-before-reassign guard at the start of the connection
setup path, mirroring the guard DiscordAdapter.connect() already has.
When self._handler is None (fresh adapter, first connect()) the block is
a harmless no-op. Scoped to the handler/app fields only — no behavior
change for any path that does not call connect() twice.
Fixes#18980
- TestClampCommandNamesTriples: unit tests for 3-tuple support in
_clamp_command_names (short names, long names, collisions, multiple
entries, backward compat with 2-tuples)
- TestDiscordSkillCmdKeyDispatch: integration test through the full
discord_skill_commands pipeline verifying long skill names retain
their original cmd_key after clamping
- Add contributor CharlieKerfoot to AUTHOR_MAP
Enable OpenRouter's response caching feature (beta) via X-OpenRouter-Cache
headers. When enabled, identical API requests return cached responses for
free (zero billing), reducing both latency and cost.
Configuration via config.yaml:
openrouter:
response_cache: true # default: on
response_cache_ttl: 300 # 1-86400 seconds
Changes:
- Add openrouter config section to DEFAULT_CONFIG (response_cache + TTL)
- Add build_or_headers() in auxiliary_client.py that builds attribution
headers plus optional cache headers based on config
- Replace inline _OR_HEADERS dicts with build_or_headers() at all 5 sites:
run_agent.py __init__, _apply_client_headers_for_base_url(), and
auxiliary_client.py _try_openrouter() + _to_async_client()
- Add _check_openrouter_cache_status() method to AIAgent that reads
X-OpenRouter-Cache-Status from streaming response headers and logs
HIT/MISS status
- Document in cli-config.yaml.example
- Add 28 tests (22 unit + 6 integration)
Ref: https://openrouter.ai/docs/guides/features/response-caching
When resolve_provider_client() passes explicit_api_key for OpenRouter auxiliary
tasks, _try_openrouter() now accepts and honors this parameter instead of
silently ignoring it and falling back to OPENROUTER_API_KEY env var.
Root cause: _try_openrouter() had no explicit_api_key parameter, so even
when callers wanted to pass a runtime credential pool key, it could not be used.
Fix:
- Add explicit_api_key: str = None parameter to _try_openrouter()
- Prioritize explicit_api_key over pool key and env var
- Update resolve_provider_client() call site to pass explicit_api_key
Regression coverage:
- Test that explicit_api_key is passed to OpenAI client when provided
- Test that fallback to OPENROUTER_API_KEY still works when explicit_api_key is None
Closes#18338
Two mitigations for the CLOSE_WAIT accumulation reported against QQ Bot
+ Feishu on macOS behind Cloudflare Warp.
1. Shared httpx.Limits helper (gateway/platforms/_http_client_limits.py).
Every long-lived platform adapter now constructs httpx.AsyncClient
with max_keepalive_connections=10 and keepalive_expiry=2.0, vs httpx's
default of unbounded keepalive pool and 5.0s expiry. On macOS/Warp the
default 5s window let idle keepalive sockets sit in CLOSE_WAIT long
enough for seven persistent adapters (QQ Bot, WeCom, DingTalk, Signal,
BlueBubbles, WeCom-callback, plus the transient Feishu helper) to
compound to the 256-fd ulimit. Tunable via
HERMES_GATEWAY_HTTPX_KEEPALIVE_EXPIRY and
HERMES_GATEWAY_HTTPX_MAX_KEEPALIVE env vars.
2. whatsapp.send_typing aiohttp leak. The call was
'await self._http_session.post(...)' with no 'async with' and no
variable capture — the ClientResponse went out of scope unclosed,
holding its TCP socket in CLOSE_WAIT until GC. Fixed by wrapping in
'async with'. This was the only bare-await aiohttp leak in the
gateway/tools/plugins tree per audit; all other aiohttp sites use
the context-manager pattern correctly.
The underlying reporter also saw Feishu SDK (lark-oapi) connections in
CLOSE_WAIT — those are inside the SDK and out of our direct control, but
tightening httpx keepalive across adapters reduces the aggregate pool
pressure regardless of which individual adapter leaks.
Snapshot Content-Type and body while the client context is still
active so pooled connections fully release on exit. Previously the
read happened after `async with httpx.AsyncClient(...)` returned —
which works today only because httpx eagerly buffers non-streaming
responses; a future refactor to `.stream()` would silently read-
after-close.
Part of the #18451 connection-hygiene audit. Salvage of #18502.
When a provider's credential pool has a single entry in 429-cooldown,
resolve_provider_client returns None and AIAgent.__init__ raises a
misleading RuntimeError suggesting the API key is missing — even when
valid fallback_providers are configured.
This patch makes __init__ iterate the fallback chain before raising,
mirroring the existing in-flight fallback logic in the request loop.
If a fallback resolves, the agent initializes against it and sets
_fallback_activated=True so _restore_primary_runtime can pick the
primary back up after cooldown.
Closes#17929
* fix(gateway): config.yaml wins over .env for agent/display/timezone settings
Regression from the silent config→env bridge. The bridge at module import
time is correct for max_turns (unconditional overwrite), but every other
agent.*, display.*, timezone, and security bridge key was guarded by
'if X not in os.environ' — so a stale .env entry from an old 'hermes setup'
run would shadow the user's current config.yaml indefinitely.
Symptom: agent.max_turns: 500 in config.yaml, HERMES_MAX_ITERATIONS=60
in .env from an old setup, and the gateway silently capped at 60
iterations per turn. Gateway logs confirmed api_calls never exceeded 60.
Three changes:
1. gateway/run.py: drop the 'not in os.environ' guards for all agent.*,
display.*, timezone, and security.* bridge keys. config.yaml is now
authoritative for these settings — same semantics already in place
for max_turns, terminal.*, and auxiliary.*. Also surface the bridge
failure (previously 'except Exception: pass') to stderr so operators
see bridge errors instead of silently falling back to .env.
2. gateway/run.py: INFO-log the resolved max_iterations at gateway
start so operators can verify the config→env bridge did the right
thing instead of chasing a phantom budget ceiling.
3. hermes_cli/setup.py: stop writing HERMES_MAX_ITERATIONS to .env in
the setup wizard. config.yaml is the single source of truth. Also
clean up any stale .env entry left behind by pre-fix setups.
Regression tests in tests/gateway/test_config_env_bridge_authority.py
guard each config→env key against the 'stale .env shadows config' bug.
* fix(gateway): shutdown + restart hygiene (drain timeout, false-fatal, success log)
Three issues observed in production gateway.log during a rapid restart
chain on 2026-05-02, all fixed here.
1. _send_restart_notification logged unconditional success
adapter.send() catches provider errors (e.g. Telegram 'Chat not found')
and returns SendResult(success=False); it never raises. The caller
ignored the return value and always logged 'Sent restart notification
to <chat>' at INFO, producing a misleading success line directly
below the 'Failed to send Telegram message' traceback on every boot.
Now inspects result.success and logs WARNING with the error otherwise.
2. WhatsApp bridge SIGTERM on shutdown classified as fatal error
_check_managed_bridge_exit() saw the bridge's returncode -15 (our own
SIGTERM from disconnect()) and fired the full fatal-error path,
producing 'ERROR ... WhatsApp bridge process exited unexpectedly' plus
'Fatal whatsapp adapter error (whatsapp_bridge_exited)' on every
planned shutdown, immediately before the normal '✓ whatsapp
disconnected'. Adds a _shutting_down flag that disconnect() sets
before the terminate, and _check_managed_bridge_exit() returns None
for returncode in {0, -2, -15} while shutting down. OOM-kill (137)
and other non-signal exits still hit the fatal path.
3. restart_drain_timeout default 60s → 180s
On 2026-05-02 01:43:27 a user /restart fired while three agents were
mid-API-call (82s, 112s, 154s into their turns). The 60s drain budget
expired and all three were force-interrupted. 180s covers realistic
in-flight agent turns; users on very-long-reasoning models can still
raise it further via agent.restart_drain_timeout in config.yaml.
Existing explicit user values are preserved by deep-merge.
Tests
- tests/gateway/test_restart_notification.py: two new tests assert INFO
is only logged on SendResult(success=True) and WARNING with the error
string is logged on SendResult(success=False).
- tests/gateway/test_whatsapp_connect.py: parametrized test for
returncode in {0, -2, -15} proves shutdown-time exits are suppressed;
separate test proves returncode 137 (SIGKILL/OOM) still surfaces as
fatal even when _shutting_down is set.
- _check_managed_bridge_exit() reads _shutting_down via getattr-with-
default so existing _make_adapter() test helpers that bypass __init__
(pitfall #17 in AGENTS.md) keep working unmodified.
Discord's per-command name limit is 32 chars. When two skill slugs
share the same first 32 chars (or a skill slug clamps onto a reserved
gateway command name), only the first seen wins — the second is
dropped from the /skill autocomplete. The old behavior incremented a
``hidden`` counter silently, so skill authors had no way to discover
the drop short of noticing their skill was missing from the picker.
Not an actively-biting bug today (no collisions on the default catalog
as of 2026-05), but a landmine the moment someone ships a skill with a
long name. The earlier series in #18745 / #18753 / #18754 dropped the
other silent data-loss paths in the Discord /skill collector; this one
lights up the last remaining one.
Fix: promote ``_names_used`` from a set to a dict keyed by the clamped
name, mapping to the source cmd_key (or a ``"<reserved>"`` sentinel
for names inherited via ``reserved_names``). On collision, log a
WARNING naming both sides — the winner, the loser, the clamped name,
and what to rename.
Two phrasings:
* skill-vs-skill — "both clamp to X on Discord's 32-char command-name
limit; only the winner appears in /skill. Rename one skill's
frontmatter ``name:`` to differ in its first 32 chars."
* skill-vs-reserved — "collides with a reserved gateway command name;
the skill will not appear in /skill. Rename the skill's frontmatter
``name:``."
Tests: three cases in
``tests/hermes_cli/test_discord_skill_clamp_warning.py`` —
skill-vs-skill collision (warning names both cmd_keys + clamped prefix),
skill-vs-reserved collision (warning uses the distinct phrasing), and a
no-collision negative (zero warnings emitted).
Covers PR #18224 fix for issue #18187 — when DiscordAdapter.connect() is
called a second time without an intervening disconnect(), the previous
commands.Bot must be closed before a new one is created. Otherwise both
websockets stay connected to Discord's gateway and both fire on_message,
producing double responses with different wording.
Covers PR #18256 fix for issue #18254 — when OPENROUTER_API_KEY is set in
BOTH os.environ (stale from parent shell) and ~/.hermes/.env (fresh),
_seed_from_env must prefer the .env value. Also guards the fallback case
where .env omits the key entirely (Docker/K8s/systemd deployments that
only inject via runtime env).
`_register_skill_group` captured the skill catalog in closure variables
(`entries` and `skill_lookup`) so the single `tree.add_command` call at
startup owned the only live copy. The closure is never re-entered after
startup, so `/reload-skills` — which rescans the on-disk skills dir and
refreshes the in-process `_skill_commands` registry — had no way to
propagate results into the `/skill` autocomplete on Discord. New skills
stayed invisible in the dropdown, and deleted skills returned
"Unknown skill" when the stale autocomplete entry was clicked.
The fix is purely a dataflow change: promote `entries` and `skill_lookup`
to instance attributes (`_skill_entries`, `_skill_lookup`), split the
collector-driven rebuild into a helper (`_refresh_skill_catalog_state`),
and add a public `refresh_skill_group()` method that re-runs the helper
and is safe to call at any point after the initial registration.
The gateway's `_handle_reload_skills_command` then iterates
`self.adapters` and calls `refresh_skill_group()` on any adapter that
exposes it (currently only Discord). Both sync and async implementations
are supported; adapters that don't override the method (Telegram's
BotCommand menu, Slack subcommand map, etc.) are silently skipped — the
in-process `reload_skills()` call covers them.
No `tree.sync()` is required because Discord fetches autocomplete
options dynamically on every keystroke — mutating the instance state the
callbacks already read from is sufficient. That sidesteps the per-app
command-bucket rate limit (~5 writes / 20 s) that made the previous
bulk-sync-on-reload approach unusable (#16713 context).
Tests: tests/gateway/test_reload_skills_discord_resync.py — five cases
covering (1) refresh replaces entries, (2) entries stay sorted after
refresh, (3) collector exception leaves cached state intact, (4)
`_refresh_skill_catalog_state` populates the instance attrs, (5)
orchestrator calls `refresh_skill_group()` on sync + async adapters and
skips adapters that don't expose it.
_check_unavailable_skill is meant to turn a typed "/foo" command that
doesn't resolve into a specific hint — "disabled, enable with hermes
skills config" or "available but not installed, install with hermes
skills install …" — instead of the generic "unknown command" reply.
It was doing the match with `skill_md.parent.name.lower().replace("_", "-")`,
comparing that to the typed command. For every skill whose directory name
drifted from its declared frontmatter `name:`, that comparison failed and
the user got the unhelpful generic path. On a standard install today 19
skills have this drift, e.g.:
dir: mlops/stable-diffusion
frontmatter: name: Stable Diffusion Image Generation
registered slug (what the user types): /stable-diffusion-image-generation
dir: mlops/qdrant
frontmatter: name: Qdrant Vector Search
registered slug: /qdrant-vector-search
dir: mlops/flash-attention
frontmatter: name: Optimizing Attention Flash
registered slug: /optimizing-attention-flash
In every case, _check_unavailable_skill would fall through because
"stable-diffusion" != "stable-diffusion-image-generation", even with the
skill sitting right there on disk.
Fix: extract a small `_skill_slug_from_frontmatter` helper that reads the
SKILL.md frontmatter and normalizes exactly like scan_skill_commands
(lower, spaces/underscores → hyphens, strip non-[a-z0-9-], collapse
runs of hyphens, strip edges). Use it in both the
disabled-skills branch and the optional-skills branch. The disabled-set
membership check now uses the declared frontmatter name (which is what
`hermes skills config` writes into skills.disabled / platform_disabled),
not the slug.
Tests: five cases in tests/gateway/test_unavailable_skill_hint.py —
the drift case for the disabled branch, unknown-command negative,
matched-but-not-disabled negative, non-alnum stripping, and the drift
case for the optional-skills branch. All five fail against main and
pass with the fix.
``discord_skill_commands_by_category`` was lagging the flat
``discord_skill_commands`` collector on two counts. Both were actively
dropping skills from Discord's ``/skill`` autocomplete dropdown.
1. External-dir skills were filtered out. #18741 widened the flat
collector to accept ``SKILLS_DIR + skills.external_dirs`` but left
this sibling collector — the one ``_register_skill_group`` actually
uses on Discord — still matching ``SKILLS_DIR`` only. External
skills were visible in ``hermes skills list`` and the agent's
``/skill-name`` dispatch but silently absent from Discord's
``/skill`` picker. Widen the accepted roots to match, and derive
categories from whichever root the skill lives under so
``<ext>/mlops/foo/SKILL.md`` still lands in the ``mlops`` group.
2. 25-group × 25-subcommand caps were still applied. PR #11580
refactored ``/skill`` to a flat autocomplete (whose options Discord
fetches dynamically — no per-command payload concern) and its
docstring promises "no hidden skills." The collector kept the old
nested-layout caps anyway, silently dropping anything past the 25th
alphabetical category. On installs with 29 category dirs today (real
example: tail categories ``social-media``, ``software-development``,
``yuanbao`` going missing) this was biting immediately. Remove the
caps; ``hidden`` now reports only 32-char name-clamp collisions
against reserved names.
Tests: guard both behaviors. ``test_no_legacy_25x25_cap`` builds 30
categories × 30 skills each and asserts all 900 are returned.
``test_external_dirs_skills_included`` monkeypatches
``get_external_skills_dirs`` and asserts an external-dir skill makes
it into the result grouped under its own top-level directory.
After a transient Telegram 502, _handle_polling_network_error's
stop()+start_polling() cycle can leave PTB's Updater with `running=True`
but a wedged consumer task that never makes progress. No error_callback
fires in that state, so the reconnect ladder never advances past attempt
1, the MAX_NETWORK_RETRIES fatal-error path is never reached, and the
gateway sits silent indefinitely.
Schedule a heartbeat probe (60s after a successful reconnect) that
verifies Updater.running is still True and bot.get_me() responds within
a tight asyncio.wait_for timeout. Either failure feeds back into the
reconnect ladder so the existing escalation path fires.
No PTB-internal coupling, no Application rebuild — minimal additive
defense inside the existing reconnect abstraction.
Tests cover healthy / Updater non-running / probe timeout / probe
network error / already-fatal cases, plus an integration check that the
probe is actually scheduled after a successful start_polling().
Closes the silent-wedge case observed in the wild after a transient
Telegram 502; existing reconnect tests updated to mock bot.get_me() now
that the success path schedules a heartbeat probe.
Providers like Google Vertex, Azure, and Amazon Bedrock reject API
requests with duplicate tool names (HTTP 400: 'Tool names must be
unique'). The upstream injection paths in run_agent.py already dedup
after PR #17335, but two API-boundary functions pass tools through
without checking:
- agent/auxiliary_client.py: _build_call_kwargs() (all non-Anthropic
providers in chat_completions mode)
- agent/anthropic_adapter.py: convert_tools_to_anthropic() (Anthropic
Messages API path)
Add defensive dedup guards at both sites. Duplicates are dropped with
a warning log, converting a hard 400 failure into a recoverable
condition. This is intentionally conservative — the root-cause dedup
in run_agent.py is the primary defense; these guards add resilience
against future injection-path regressions.
Includes 8 new tests covering unique passthrough, duplicate removal,
empty/None edge cases.
Closes#18478
When HERMES_HOME is unset but ~/.hermes/active_profile names a non-default
profile, any data this process writes lands in the default profile — not the
one the operator expects. Before this change the fallback was silent, so
cross-profile contamination (#18594) was invisible until a user noticed
their memory/state ended up in the wrong place.
Now we emit a one-shot warning to stderr the first time this happens in
a process. No raise — there are 30+ module-level callers of get_hermes_home()
and raising from any of them would brick import. Behavior is otherwise
unchanged; subprocess spawners (systemd template, kanban dispatcher, docker
entrypoint) already propagate HERMES_HOME correctly.
Bypasses logging.getLogger() because this runs before logging is configured
in a significant fraction of callers (module import time).
Refs #18594. Credit to @liuhao1024 for surfacing the silent-fallback case
in PR #18600; we kept the diagnostic signal without the import-time raise.
Path.read_text() uses the system locale by default. On Windows CN/JP/KR
locales (GBK/CP932/CP949), reading a UTF-8 .env raises UnicodeDecodeError
as soon as it contains any non-ASCII byte (e.g. an em dash).
Pin encoding="utf-8" on every .env read in hermes_cli to match how the
rest of the codebase (load_dotenv at doctor.py:26) already decodes it.
Adds a regression test that monkeypatches Path.read_text to simulate a
GBK locale and asserts 'hermes doctor' no longer raises.
Refs #18637
Skills configured through `skills.external_dirs` in config.yaml were
visible via `hermes skills list`, `get_skill_commands()`, and the
agent's `/skill-name` dispatch, but silently excluded from the
Telegram and Discord slash-command menus. The filter in
`_collect_gateway_skill_entries` only accepted skills whose
`skill_md_path` started with `SKILLS_DIR`, so anything under an
external directory fell through.
Widen the accepted-prefix set to include all configured external
dirs alongside the local skills dir. Every prefix is now
slash-terminated so `/my-skills` cannot also admit
`/my-skills-extra`. Also guard against empty `skill_md_path`
values so they can't accidentally match.
Fixes#8110
Salvages #8790 by luyao618.
Co-authored-by: Yao <34041715+luyao618@users.noreply.github.com>
The process-global `_skill_commands` dict in agent/skill_commands.py
was seeded by whichever platform scanned first, and
`get_skill_commands()` only rescanned when the cache was empty. In a
long-lived gateway process serving multiple platforms (Telegram +
Discord + Slack), the first platform's
`skills.platform_disabled` view was silently inherited by the
others — so a skill disabled for Telegram would also disappear from
Discord's slash menu, and vice versa.
Track the platform scope the cache was populated for
(`_skill_commands_platform`) and rescan in `get_skill_commands()`
when the currently-active platform no longer matches. Platform
resolution uses the same precedence as `_is_skill_disabled`:
`HERMES_PLATFORM` env var then `HERMES_SESSION_PLATFORM` from the
gateway session context.
Fixes#14536
Salvages #14570 by LeonSGP43.
Co-authored-by: LeonSGP <leon@sgp43.com>
* fix(curator): authoritative absorbed_into declarations on skill delete
Closes#18671. The classification pipeline that feeds cron-ref rewriting
used to infer consolidation vs pruning from two brittle signals: the
curator model's post-hoc YAML summary block, and a substring heuristic
scanning other tool calls for the removed skill's name. Both miss in
real consolidations — the model forgets the YAML under reasoning
pressure, and the heuristic misses when the umbrella's patch content
describes the absorbed behavior abstractly instead of naming the old
slug. When both miss, the skill falls through to 'no-evidence fallback'
pruned, and #18253's cron rewriter drops the cron ref entirely instead
of mapping it to the umbrella. Same observable symptom as pre-#18253:
'Skill(s) not found and skipped' at the next cron run.
The fix makes the model declare intent at the moment of deletion.
skill_manage(action='delete') now accepts absorbed_into:
- absorbed_into='<umbrella>' -> consolidated, target must exist on disk
- absorbed_into='' -> explicit prune, no forwarding target
- missing -> legacy path, falls through to heuristic/YAML
The curator reconciler reads these declarations off llm_meta.tool_calls
BEFORE either the YAML block or the substring heuristic. Declaration
wins. Fallback logic stays intact for backward compat with any caller
(human or older curator conversation) that doesn't populate the arg.
Changes
- tools/skill_manager_tool.py: add absorbed_into param to skill_manage
+ _delete_skill. Validate target exists when non-empty. Reject
absorbed_into=<self>. Wire through dispatcher + registry + schema.
- agent/curator.py: new _extract_absorbed_into_declarations() walks
tool calls for skill_manage(delete) with the arg. _reconcile_classification
accepts absorbed_declarations= and treats them as authoritative. Curator
prompt updated to require the arg on every delete.
- Tests: 7 new skill_manager tests covering the tool contract (valid
target, empty string, nonexistent target, self-reference, whitespace,
backward compat, dispatcher plumbing). 11 new curator tests covering
the extractor + authoritative reconciler path + mixed-legacy-and-
declared runs.
Validation
- 307/307 targeted tests pass (curator + cron + skill_manager suites).
- E2E #18671 repro: 3 narrow skills, 1 umbrella, cron job referencing
all 3. Model emits NO YAML block. Heuristic misses (patch prose
doesn't name old slugs). Delete calls carry absorbed_into. Result:
both PR skills correctly classified 'consolidated' + cron rewritten
['pr-review-format', 'pr-review-checklist', 'stale-junk'] ->
['hermes-agent-dev']; stale-junk pruned via absorbed_into=''.
- E2E backward-compat: delete without absorbed_into, model emits YAML
-> routed via existing 'model' source, cron still rewritten correctly.
* feat(curator): capture + restore cron skill links across snapshot/rollback
Before this, rolling back a curator run restored the skills tree but cron
jobs still pointed at the umbrella skills the curator had rewritten them
to. The user would see their old narrow skills back on disk but their
cron jobs still configured with the merged umbrella — not actually 'back
to how it was'.
Snapshot side: snapshot_skills() now captures ~/.hermes/cron/jobs.json
alongside the skills tarball, as cron-jobs.json. The manifest gets a new
'cron_jobs' block with {backed_up, jobs_count} so rollback (and the CLI
confirm dialog) can surface what's in the snapshot. If jobs.json is
missing/unreadable/malformed, snapshot proceeds without cron data — the
skills backup is the core guarantee; cron is additive.
Rollback side: after the skills extract succeeds, the new
_restore_cron_skill_links() reconciles the backed-up jobs into the live
jobs.json SURGICALLY. Only 'skills' and 'skill' fields are restored, and
only on jobs matched by id. Everything else about a cron job — schedule,
last_run_at, next_run_at, enabled, prompt, workdir, hooks — is live
state the user or scheduler has modified since the snapshot; overwriting
it would regress unrelated activity.
Reconciliation rules:
- Job in backup AND live, skills differ → skills restored.
- Job in backup AND live, skills match → no-op.
- Job in backup, NOT in live → skipped (user deleted it
after snapshot; their choice
is later than the snapshot).
- Job in live, NOT in backup → untouched (user created it
after snapshot).
- Snapshot missing cron-jobs.json at all → rollback still succeeds,
reports 'not captured'
(older pre-feature snapshots
keep working).
Writes go through cron.jobs.save_jobs under the same _jobs_file_lock the
scheduler uses, so rollback doesn't race tick().
Also:
- hermes_cli/curator.py: rollback confirm dialog now shows
'cron jobs: N (will be restored for skill-link fields only)' when the
snapshot has cron data, or 'not in snapshot (<reason>)' otherwise.
- rollback()'s message string includes a 'cron links: ...' clause
summarizing the reconciliation outcome.
Tests
- 9 new cases: snapshot-with-cron, snapshot-without-cron, malformed-json
captured-as-raw, full rollback-restores-skills-and-cron, rollback
touches only skill fields, rollback skips user-deleted jobs, rollback
leaves user-created jobs untouched, rollback still works with
pre-feature snapshot that has no cron-jobs.json, standalone unit test
on _restore_cron_skill_links exercising the full report shape.
Validation
- 484/484 targeted tests pass (curator + cron + skill_manager suites).
- E2E: real snapshot_skills, real cron rewrite, real rollback. Before:
['pr-review-format', 'pr-review-checklist', 'pr-triage-salvage'].
After curator: ['hermes-agent-dev']. After rollback: ['pr-review-format',
'pr-review-checklist', 'pr-triage-salvage']. Non-skill fields (id,
name, prompt) preserved across the round trip.
FixesNousResearch/hermes-agent#11768
Root cause: target.strip().lower() was lowercasing the entire target string,
corrupting case-sensitive chat IDs like Slack C123ABC and Matrix !RoomABC.
Fix: Only lowercase the platform prefix for case-insensitive matching;
preserve the original case for chat_id and thread_id values.
YAML loads a bare numeric value such as
discord:
free_response_channels: 1491973769726791812
as an int. _discord_free_response_channels() / _slack_free_response_channels()
checked `isinstance(raw, list)` and `isinstance(raw, str)` in that order and
then fell through to `return set()`, so a single-channel config that happened
to be unquoted was silently dropped with no log line — the bot kept demanding
@mentions even though the channel was configured to free-response.
A multi-channel value like `1234567890,9876543210` does not trip this because
the comma forces YAML to parse it as a string. Single-channel configs are
the only case that breaks, which is exactly the footgun that's hardest to
diagnose (the config "looks right" and the feature just doesn't activate).
Note that the old-schema env-var bridge at gateway/config.py:614+ already
runs `str(frc)` when forwarding to SLACK_/DISCORD_FREE_RESPONSE_CHANNELS,
so the env-var fallback worked. The bug only surfaces on the
`config.extra["free_response_channels"]` path populated by the `platforms:`
bridge at gateway/config.py:576, which passes the raw YAML value through
unchanged.
Fix at the reader: treat any non-list value as a scalar, coerce with str(),
then apply the same CSV split semantics. This keeps the public contract
stable (list or str-like continues to work identically) while accepting
the ints that the YAML loader is free to hand us.
Added tests for both Discord and Slack covering:
- bare int value in config.extra
- list of ints in config.extra
Slack has built-in slash commands (e.g. /status, /me, /join) that apps
cannot register. When running `hermes slack manifest --write`, the
generated manifest included /status, causing Slack to reject the entire
manifest with a reserved-command error.
Add _SLACK_RESERVED_COMMANDS frozenset of all known Slack built-ins and
skip them in slack_native_slashes(). Affected commands remain reachable
via /hermes <command>.
Tests updated:
- New test_excludes_slack_reserved_commands validates no leaks
- test_includes_canonical_commands no longer asserts /status
- test_telegram_parity accounts for expected Slack-only exclusions
Self-review fixes for the slash ephemeral ack:
- Only stash response_url when text starts with '/' (gateway command).
Free-form questions via '/hermes <question>' must produce public agent
replies visible to the whole channel, not ephemeral.
- Use a ContextVar (_slash_user_id) to thread the invoking user's ID
from _handle_slash_command through to send(). _pop_slash_context now
matches the exact (channel_id, user_id) key when the ContextVar is
set, preventing concurrent users on the same channel from stealing
each other's ephemeral context. ContextVars propagate to child
asyncio.Tasks, so the value survives through handle_message →
_process_message_background → _send_with_retry → send().
- Add truncate_message() in _send_slash_ephemeral to prevent silent
failures on long responses (response_url has the same ~40k limit).
- Log send_private_notice failures at debug level instead of bare
except/pass — aids diagnostics without spamming.
- Document app_mention dedup dependency on shared event ts.
- Add tests: free-form question must NOT stash context, concurrent
users on the same channel get isolated contexts, non-slash send()
path fallback behavior.
Adds platform-level private notice delivery abstraction so operational
messages (e.g. sethome prompt) can be sent ephemerally on Slack when
configured with `slack.notice_delivery: private`.
Changes:
- gateway/config.py: _normalize_notice_delivery() + GatewayConfig.get_notice_delivery()
with per-platform config bridging
- gateway/platforms/base.py: send_private_notice() default implementation
(falls through to send())
- gateway/platforms/slack.py: send_private_notice() via chat_postEphemeral
- gateway/run.py: _deliver_platform_notice() helper replaces direct
adapter.send() for the sethome notice, with private→public fallback
- gateway/platforms/slack.py: app_mention handler now forwards to
_handle_slack_message (safe due to ts-based dedup) instead of no-op pass,
fixing edge-case Slack configs where mentions arrive only as app_mention
- gateway/platforms/slack.py format_message: negative lookbehind prevents
markdown images (![]()) from becoming broken Slack links; italic regex
now requires non-whitespace boundaries so 'a * b * c' stays literal
Based on PR #9340 by @probepark.
Slack slash commands (/q, /btw, /stop, /model, etc.) previously showed
no user-visible acknowledgement and posted command replies as public
channel messages. This diverged from Discord, which uses ephemeral
deferred responses for slash commands.
Changes:
- handle_hermes_command now passes response_type='ephemeral' and a
'Running /cmd…' text to ack(), giving the user immediate 'Only visible
to you' feedback when they invoke any native slash command.
- _handle_slash_command stashes the Slack response_url from the command
payload in a per-channel context dict before dispatching to
handle_message.
- send() checks for a pending slash context and, when found, POSTs to
the response_url with replace_original=true to swap the initial ack
with the real command reply (e.g. 'Queued for the next turn.'),
keeping it ephemeral.
- Stale slash contexts are garbage-collected on lookup (120s TTL).
- The response_url POST is non-fatal: if it fails, the user already saw
the initial ack, and send() returns success=True.
Fixes#18182
Long-running gateway processes that survive 'hermes update' keep
pre-update modules cached in sys.modules. When new tool files on
disk then try to 'from hermes_cli.config import cfg_get' (added in
PR #17304), the import resolves against the stale module object
and raises ImportError — hitting users on Matrix, Telegram, Feishu,
and other platforms.
Two defenses:
1. Gateway self-check (gateway/run.py). On __init__, snapshot the
newest mtime across sentinel source files (hermes_cli/config.py,
run_agent.py, gateway/run.py, etc.). On every inbound message,
re-read those mtimes; if any is newer than boot time + 2s slack,
request a graceful restart via the normal drain path and return
a one-line ack to the user. Idempotent, works regardless of how
the update happened (hermes update, manual git pull, installer).
2. Post-restart survivor sweep ('hermes update'). After the existing
restart loop, sleep 3s, rescan for gateway PIDs we already tried
to kill, and SIGKILL any survivors. The detached profile watchers
and systemd then relaunch with fresh code instead of waiting out
the 120s watcher timeout.
Closes#17648.
* fix(curator): defer first run and add --dry-run preview (#18373)
Curator was meant to run 7 days after install, not on the very first
gateway tick. On a fresh install (no .curator_state), should_run_now()
returned True immediately because last_run_at was None — so the gateway
cron ticker fired Curator against a fresh skill library moments after
'hermes update'. Combined with the binary 'agent-created' provenance
model (anything not bundled and not hub-installed), this consolidated
hand-authored user workflow skills without consent.
Changes:
- should_run_now(): first observation seeds last_run_at='now' and returns
False. The next real pass fires one full interval_hours later (7 days
by default), matching the original design intent.
- hermes curator run --dry-run: produces the same review report without
applying automatic transitions OR permitting the LLM to call
skill_manage / terminal mv. A DRY-RUN banner is prepended to the
prompt and the caller skips apply_automatic_transitions. State is
NOT advanced so a preview doesn't defer the next scheduled real pass.
- hermes update: prints a one-liner on fresh installs pointing at
--dry-run, pause, and the docs. Silent on steady state.
- Docs: curator.md and cli-commands.md explain the deferred first-run
behavior and warn that hand-written SKILL.md files share the
'agent-created' bucket, with guidance to pin or preview before the
first pass.
Tests:
- test_first_run_defers replaces the old 'first run always eligible'
assertion — same fixture, inverted expectation.
- test_maybe_run_curator_defers_on_fresh_install covers the gateway tick
path end-to-end.
- Three new dry-run tests cover state-advance suppression, prompt
banner injection, and apply_automatic_transitions skipping.
Fixes#18373.
* feat(curator): pre-run backup + rollback (#18373)
Every real curator pass now snapshots ~/.hermes/skills/ into
~/.hermes/skills/.curator_backups/<utc-iso>/skills.tar.gz before calling
apply_automatic_transitions or the LLM review. If a run consolidates or
archives something the user didn't want touched, 'hermes curator
rollback' restores the tree in one command. Dry-run is skipped — no
mutation means no snapshot needed.
Changes:
- agent/curator_backup.py (new): tar.gz snapshot + safe rollback. The
snapshot excludes .curator_backups/ (would recurse) and .hub/ (managed
by the skills hub). Extract refuses absolute paths and .. components,
and uses tarfile's filter='data' on Python 3.12+. Rollback takes a
pre-rollback safety snapshot FIRST, stages the current tree into
.rollback-staging-<ts>/ so the extract lands in an empty dir, and
cleans the staging dir on success. A failed extract restores the
staged contents.
- agent/curator.py: run_curator_review() calls curator_backup.
snapshot_skills(reason='pre-curator-run') before apply_automatic_
transitions. Best-effort — a failed snapshot logs at debug and the
run continues (a transient disk issue shouldn't silently disable
curator forever).
- hermes_cli/curator.py: new 'hermes curator backup' and 'hermes curator
rollback' subcommands. rollback supports --list, --id <ts>, -y.
- hermes_cli/config.py: curator.backup.{enabled, keep} config block
with sane defaults (enabled=true, keep=5).
- Docs: curator.md gets a 'Backups and rollback' section; cli-commands
.md table gets the new rows.
Tests (new file tests/agent/test_curator_backup.py, 16 cases):
- snapshot creates tarball + manifest with correct counts
- snapshot excludes .curator_backups/ (recursion guard) and .hub/
- snapshot disabled via config returns None without creating anything
- snapshot uniquifies ids within the same second (-01 suffix)
- prune honors keep count, newest-first
- list_backups + _resolve_backup cover newest-default and unknown-id
- rollback restores a deleted skill with content intact
- rollback is itself undoable — safety snapshot shows up in list_backups
- rollback with no snapshots returns an error
- rollback refuses tarballs with absolute paths or .. components
- real curator runs take a 'pre-curator-run' snapshot; dry-runs do not
All curator tests: 210 passing locally.
Prevents ghost sessions from accumulating in state.db when the TUI/web
dashboard is opened and closed without sending a message.
Changes:
- run_agent.py: Add _ensure_db_session() gate method, called at
run_conversation() entry. Remove eager create_session() from __init__.
Handle compression rotation flag correctly.
- tui_gateway/server.py: Remove eager db.create_session() in
_start_agent_build(). Add post-first-message pending_title re-apply.
- hermes_state.py: Extract _insert_session_row() shared helper (DRY).
Add prune_empty_ghost_sessions() for one-time migration.
- cli.py: One-time ghost session prune on startup. Fix _pending_title
to call _ensure_db_session() before set_session_title().
- hermes_cli/main.py: Guard TUI exit summary on message_count > 0.
- tests: Update test_860_dedup to call _ensure_db_session() before
direct _flush_messages_to_session_db() calls.
Closes: ghost session clutter in hermes sessions list and web dashboard.
The anyOf collapse in _repair_schema returned early, skipping the
nullable-strip and enum-cleanup steps. When a schema had anyOf
[{enum: [..., null, '']}, {type: null}] alongside a parent-level
'nullable: true', collapsing to the single non-null branch produced a
merged node that still had both 'nullable' and the bad enum values —
Moonshot would still 400 on it.
Fix: fall through to Rules 1/3 when the collapse produces a single
merged node; only return early for the multi-branch case (pure
anyOf preservation) or when there was no null branch to remove.
Adds a test that locks in the combined-case expectation.
When a schema node inside anyOf has enum values but no explicit 'type',
Rule 3 (enum cleanup) ran before _fill_missing_type, so node_type was
None and the enum was never cleaned. Moonshot then rejected the schema
with 'enum value (<nil>) does not match any type in [string]'.
Fix: reorder operations — fill missing type first, strip nullable,
then clean enum. This ensures enum cleanup always has a type to check.
Also fixes test expectation: empty string in enum is now correctly
stripped (Moonshot rejects it too).
Closes#16875
Add a standing-goal slash command that keeps Hermes working toward a
user-stated objective across turns until it is achieved, paused, or
the turn budget runs out. Our take on the Ralph loop — cf. Codex CLI
0.128.0's /goal.
After each turn, a lightweight auxiliary-model judge call asks 'is
this goal satisfied by the assistant's last response?'. If not, and
we're under the turn budget (default 20), Hermes feeds a continuation
prompt back into the same session as a normal user message. Any real
user message preempts the continuation loop automatically.
Judge failures fail OPEN (continue) so a flaky judge never wedges
progress — the turn budget is the real backstop.
### Commands
- `/goal <text>` — set a standing goal (kicks off the first turn)
- `/goal` or `/goal status` — show current state
- `/goal pause` — pause the continuation loop
- `/goal resume` — resume (resets turn counter)
- `/goal clear` — drop the goal
Works on both CLI and gateway platforms via the central CommandDef
registry.
### Design invariants preserved
- **Prompt cache**: continuation prompts are regular user-role
messages appended to history. No system-prompt mutation, no toolset
swap.
- **Role alternation**: continuation is a user turn, never injected
mid-tool-loop.
- **Session persistence**: goal state lives in SessionDB.state_meta
keyed by `goal:<session_id>`, so `/resume` picks it up.
- **Mid-run safety**: on the gateway, `/goal status|pause|clear` are
allowed mid-run (control-plane only); setting a new goal requires
`/stop` first so we don't race a second continuation prompt against
the current turn.
### Files
- `hermes_cli/goals.py` (new, 380 lines) — GoalManager + judge + state
- `hermes_cli/commands.py` — CommandDef entry
- `hermes_cli/config.py` — `goals.max_turns` default
- `hermes_cli/web_server.py` — dashboard category merge
- `cli.py` — /goal handler + post-turn continuation hook in
process_loop
- `gateway/run.py` — /goal handler + post-turn continuation hook
wrapping _handle_message_with_agent
- `tests/hermes_cli/test_goals.py` (new, 26 tests) — judge parsing,
fail-open semantics, lifecycle, persistence, budget exhaustion
- `website/docs/reference/slash-commands.md` — docs entry
hermes update had two interactive [Y/n] prompts with no bypass:
1. Config migration (after new env/config options are added)
2. Autostash restore (when uncommitted work was stashed before pull)
hermes uninstall already has --yes/-y; mirrors that.
Under --yes:
- Config-migrate prompt → auto-yes, migrate_config(interactive=False)
so new config fields are applied but API-key prompts are skipped
(user runs 'hermes config migrate' later for those). Matches
gateway-mode semantics.
- Stash-restore prompt → auto-yes, git stash apply runs automatically.
Closes the 'can I hermes update -y, No ! Fix' gap reported by @murelux.
Adds opt-in auto-deletion for slash-command reply messages like
"New session started!", "Restarting gateway…", "Stopped.", and
YOLO toggles. After the TTL elapses the gateway calls the adapter's
delete_message; on platforms without a delete API (everything except
Telegram today) the TTL is silently ignored and the message stays.
Requested on Twitter by @charlesmcdowell — tool-call bubbles are useful
real-time, but system notices clutter the thread once the agent finishes.
Implementation:
- EphemeralReply(str) sentinel in gateway/platforms/base.py. Subclasses
str so existing 'X' in response / response.startswith(...) checks in
tests and call sites keep working unchanged; isinstance() still
distinguishes it for the send path.
- _process_message_background and both busy-session bypass paths
(in base.py) call _unwrap_ephemeral() on the handler return, send
the unwrapped text, and schedule a detached delete task when the
TTL > 0 AND the adapter class overrides delete_message.
- display.ephemeral_system_ttl (default 0 = disabled) in DEFAULT_CONFIG.
Handler can pass ttl_seconds explicitly to override.
- Wrapped the highest-noise return sites: /new, /reset, /stop,
/yolo on/off, /restart success + "already in progress". Draining
notices and /help output left as plain strings — those are
informational and users want to read them.
Backward-compat: default TTL 0 → no scheduling, no behavior change
for existing users. Platforms without delete_message silently no-op.
When the curator consolidates skill X into umbrella Y, any cron job
that listed X in its skills field would fail to load X at run time —
the scheduler logs a warning and skips it, so the scheduled job runs
without the instructions it was scheduled to follow.
cron.jobs.rewrite_skill_refs(consolidated, pruned) now updates jobs
in-place: consolidated names route to the umbrella target (dedup
when umbrella is already present), pruned names are dropped.
agent.curator._write_run_report calls it after classification,
best-effort so a cron-side failure never breaks the curator itself.
Results are recorded in run.json (counts.cron_jobs_rewritten + full
cron_rewrites payload), a separate cron_rewrites.json for convenience
when jobs were touched, and a section in REPORT.md.
Reported by @tombielecki.
DeepSeek V4 Pro tightened thinking-mode validation and rejects empty-string
reasoning_content with HTTP 400:
The reasoning content in the thinking mode must be passed back to the API.
run_agent.py injected "" at three fallback sites — the tool-call pad in
_build_assistant_message and both injection branches of
_copy_reasoning_content_for_api (cross-provider poison guard + unconditional
thinking pad). All three now emit " " (single space), which satisfies the
non-empty check on V4 Pro without leaking fabricated reasoning.
Also upgrades stale empty-string placeholders on replay: sessions persisted
before this change have reasoning_content="" pinned at creation time; when
the active provider enforces thinking-mode echo, the replay path now rewrites
"" -> " " so existing users don't 400 on their first V4 Pro turn after
updating. Non-thinking providers still round-trip "" verbatim.
Updates 9 existing assertions + adds 2 regression tests (stale-placeholder
upgrade, non-thinking verbatim preservation).
Refs #15250, #17400.
Closes#17341.
The user-visible /compress banner and the post-compression last_prompt_tokens
writeback both counted only the raw message transcript (chars/4). With a 15KB
system prompt and 30 tool schemas (~26KB), a 4-message transcript that looks
like ~45 tokens to the transcript-only estimator is really ~10.5K tokens of
request pressure — a 234x gap.
Two user-facing consequences:
- Banner shows 'Compressing … (~45 tokens)…' while compression is actually
firing on 10K+ tokens of real pressure, confusing users about why
compression triggered (reported by @codecovenant on X; #6217).
- Post-compression last_prompt_tokens writeback omits tool schemas, so the
next should_compress() check compares real usage against a stale
underestimate — compression triggers late, potentially past the model's
context limit on small-context models (#14695).
Swap estimate_messages_tokens_rough() for estimate_request_tokens_rough()
at every user-visible banner and at the post-compression writeback.
estimate_request_tokens_rough() already existed for exactly this purpose
and includes system prompt + tool schemas.
Touched call sites:
- run_agent.py: post-compression last_prompt_tokens writeback, post-tool
call should_compress() fallback when provider usage is missing
- cli.py: /compress banner + summary
- gateway/run.py: gateway /compress banner + summary
- tui_gateway/server.py: TUI /compress status + summary
- acp_adapter/server.py: ACP /compact before/after
Left intentionally alone:
- Session-hygiene fallback and the 'no agent' /status path in gateway/run.py
— no agent instance is in scope to query for system prompt/tools, and the
existing 30-50% overestimate wobble on hygiene is safety-accepted.
- Verbose-mode 'Request size' logging — informational only, already counts
system prompt via api_messages[0].
Also relabels the feedback line from 'Rough transcript estimate' to
'Approx request size' so the metric label matches what it actually measures.
Credits: diagnoses from @devilardis (#14695) and @Jackten (#6217);
user report @codecovenant on X (2026-04-30).
Closes#14695Closes#6217
When a user types /steer <text> on an ACP session that isn't actively
running a turn (and there's no interrupted-prompt salvage available),
_cmd_steer silently appended to state.queued_prompts and replied
"No active turn — queued for the next turn". That looks identical to
/queue output even though the user never typed /queue — @EddyLeeKhane
reported this as "/steer never works, gets queued instead".
Rewrite the payload to a plain user prompt before the slash-intercept
fires, matching the gateway's idle-/steer fallthrough in
gateway/run.py ~L4898.
_process_message_background snapshotted callback_generation from the
interrupt event at the TOP of the task — before the handler ran.
_hermes_run_generation is only set on the event by
GatewayRunner._bind_adapter_run_generation during
_handle_message_with_agent, which runs DURING the handler await. The
early snapshot always captured None, which then flowed into
pop_post_delivery_callback(..., generation=None) in the finally block.
In pop_post_delivery_callback, generation=None with a tuple-registered
entry (generation, callback) bypasses the ownership check — it pops and
fires the callback regardless of which run owns it. Result: a stale run
could fire a fresher run's post-delivery callback (e.g. a
background-review notification attributed to the wrong turn).
Fix: move the snapshot into the finally block, after the handler has
run and _hermes_run_generation has been bound to the current run.
Regression test added: simulates a stale handler at generation=1 and a
fresher callback registered at generation=2. Pre-fix: snapshot=None →
pop fires the generation=2 callback under generation=1's ownership
("newer" fires). Post-fix: snapshot=1 → pop skips the mismatched
entry, callback stays in the dict for the correct run to claim.
Verified: test FAILS on current main (captures "newer" in fired list),
PASSES with this fix.
Salvaged from PR #12565 (the callback-ownership portion only; the
/status totals portion was already fixed on main in 7abc9ce4d via #17158).
Co-authored-by: Oxidane-bot <1317078257maroon@gmail.com>
Widens #16528 to two sibling sites that had the same quoted-boolean
bug: a YAML string "false" (or "0", "no", "off") silently evaluated
truthy under bool() / if-check.
- gateway/run.py _load_show_reasoning: is_truthy_value wrap
- tools/skill_manager_tool.py _guard_agent_created_enabled: is_truthy_value wrap
- regression tests for both
SELECT in get_messages_as_conversation() was missing finish_reason, so
assistant messages round-tripped through replay (including /branch copies)
silently dropped the provider's stop signal. Adds it to the SELECT, restores
it on assistant rows, and locks it in with a round-trip test.
When running on a host with sudoers NOPASSWD configured for the current
user, interactive Hermes sessions were unnecessarily entering the
password prompt path before executing sudo commands. Outside Hermes,
`sudo -n true` exits 0 for that user.
Add `_sudo_nopasswd_works()` that probes `sudo -n true` and, when it
succeeds, lets `_transform_sudo_command()` return the command unchanged
with no stdin password. The probe:
- Is scoped to the `local` terminal backend only, so Docker/SSH/Modal
and other remote backends do not inherit host sudo state.
- Re-probes every call (no process-lifetime cache) so an expired sudo
timestamp cannot silently make a later command block waiting for a
password that Hermes never prompts for.
- Is bypassed entirely when `SUDO_PASSWORD` is configured or a cached
password already exists, preserving existing explicit-password flows.
Co-authored-by: Junting Wu <juntingpublic@gmail.com>
The fix for this bug (isinstance guard) was merged via commit 3ff9e010,
but test coverage was not included. Adding 4 tests:
- dict metadata with hermes keys (normal case)
- string metadata (bug case — previously caused AttributeError)
- None metadata
- missing metadata key
Proves token A's detected capabilities do not leak to token B after the
fix in the preceding commit. Before the fix this test would have seen
both tokens return token A's cached value.
Add two operator-facing toggles for inbound Feishu admission, enabling
bot-to-bot scenarios such as A2A orchestration and inter-bot
notifications:
FEISHU_ALLOW_BOTS=none|mentions|all (default: none)
Accept messages from other bots. `mentions` requires the peer
bot to @-mention Hermes; `all` admits every peer-bot message.
FEISHU_REQUIRE_MENTION=true|false (default: true)
Whether group messages must @-mention the bot. Override per-chat
via `group_rules.<chat_id>.require_mention` in config.yaml.
Defaults preserve prior behavior. Self-echo protection is always on:
when the bot's identity is unresolved (auto-detection failed and
FEISHU_BOT_OPEN_ID unset), peer-bot messages are rejected fail-closed
to avoid feedback loops.
Admitted peer bots bypass the human-user allowlist
(FEISHU_ALLOWED_USERS) to match existing Discord behavior; humans
still need an explicit allowlist entry. yaml feishu.allow_bots is
bridged to the env var so the adapter and gateway auth layer share
one source of truth.
Resolving peer-bot display names requires the
application:bot.basic_info:read scope; without it, peers still route
but appear as their open_id.
Test: tests/gateway/test_feishu_bot_admission.py covers the admission
pipeline, group-policy bot-bypass, hydration, and event-dispatch
plumbing as a parametrized matrix.
Change-Id: I363cccb578c2a5c8b8bf0f0a890c01c89909e256
reset_session() creates a fresh SessionEntry with created_at == updated_at,
but get_or_create_session() bumps updated_at on the next inbound message,
causing _is_new_session in _handle_message_with_agent to evaluate False.
The topic/channel skill auto-load gate (group_topics, channel_skill_bindings)
silently skips the first message after a manual reset.
Add an is_fresh_reset flag on SessionEntry, set by reset_session() and
consumed once by the message handler. Kept distinct from was_auto_reset
because that flag also drives a 'session expired due to inactivity'
user-facing notice and a context-note prepend — both wrong for an
explicit /new or /reset.
Persisted through to_dict/from_dict so the flag survives gateway
restart between /reset and the next message.
Fixes#6508
Co-authored-by: warabe1122 <45554392+warabe1122@users.noreply.github.com>
Co-authored-by: willy-scr <187001140+willy-scr@users.noreply.github.com>
/status was reading session_entry.total_tokens from the in-memory
SessionStore (gateway/session.py), which the agent never writes to —
so the token count was always 0.
The agent already persists token deltas to the SQLite SessionDB
(run_agent.py:11497) for every platform with a session_id. Route
/status through that single source of truth instead of duplicating
token writes into a second store.
Fix:
- gateway/run.py: _handle_status_command now calls
self._session_db.get_session(session_id) and sums the five token
component columns (input/output/cache_read/cache_write/reasoning).
Falls back to 0 when no SessionDB is configured or no row exists.
- Two new regression tests covering the populated-row and
missing-row paths.
Co-authored-by: Hermes <127238744+teknium1@users.noreply.github.com>
sqlite3 can only bind str/bytes/int/float/None to query parameters.
Multimodal message content is a list of parts (text + image_url), which
raised 'Error binding parameter 3: type list is not supported' in
append_message and replace_messages.
In the CLI/TUI this surfaced as a visible crash when users pasted
screenshots. In the gateway it was silently swallowed by a bare except
in append_to_transcript, causing multimodal turns to be lost from the
session transcript.
Fix at the DB layer: _encode_content wraps lists/dicts as
'\\x00json:' + json.dumps(...) on write, _decode_content unwraps on
read. Plain strings are untouched, so existing FTS search, previews,
and JSONL compat are unaffected. Paired decode in get_messages,
get_messages_as_conversation, and search_messages context previews.
Regression test covers: list content round-trip, dict content
round-trip, string content stored unchanged, replace_messages with
multimodal content.
Also included: aligned fix#17522 for TUI image attachment with
paths containing spaces (see previous commit).
Remove frontend regex pre-check that truncated paths containing spaces,
quotes, or Windows drive letters. Backend _detect_file_drop correctly
handles these patterns. This fixes image attachment for common filenames
like "Screenshot 2026-04-29.png".
Add tests:
- test_input_detect_drop_path_with_spaces: attaches image with spaces in name
- test_input_detect_drop_path_with_spaces_and_remainder: remainder handling
Also restored missing in test_rollback_restore_resolves_number_and_file_path.
Scope: tui, vision, tests
When a user defines `custom_providers: [{name: kimi, ...}]` and references
`provider: kimi` from fallback_model or the main config, the built-in alias
rewriting (`kimi` → `kimi-coding`) was hijacking the request before the
named-custom lookup ran. `_get_named_custom_provider` also refused to
return a match when the raw name resolved to any built-in (including aliases),
so the custom endpoint was unreachable.
Fix at both layers of the resolution chain so every caller benefits, not
just `_try_activate_fallback`:
- hermes_cli/runtime_provider.py: narrow `_get_named_custom_provider`'s
built-in-wins guard to canonical provider names only. An alias like
`kimi` that resolves to a different canonical (`kimi-coding`) no longer
blocks the custom lookup; a canonical name like `nous` still does.
- agent/auxiliary_client.py: in `resolve_provider_client`, try the named-
custom lookup with the original (pre-alias-normalization) name before the
alias-normalized one, so aliased requests reach the user's custom entry.
Also honour `explicit_base_url` and `explicit_api_key` in the API-key
provider branch so callers that pass explicit hints (e.g. fallback
activation) can override the registered defaults.
Tests added for:
- custom `kimi` shadowing built-in alias (regression for #15743)
- custom `nous` NOT shadowing canonical built-in (behaviour preserved)
- bare `kimi` without any custom entry still routing to built-in
- explicit base_url/api_key override on the API-key provider branch
Original PR #17827 by @Feranmi10 identified the same bug class and
implemented a narrower fix in `_try_activate_fallback`; this reshapes the
fix to live in the shared resolution layer so all callers benefit.
Fixes#15743
Co-authored-by: Feranmi10 <89228157+Feranmi10@users.noreply.github.com>
Follow-up to the previous commit. Replace the post-fetch Python re-sort (which
required dropping LIMIT/OFFSET from SQL and scanning every session row) with a
recursive CTE that walks compression-continuation chains and computes
effective_last_active per root at SQL level. The outer query can then ORDER BY
+ LIMIT efficiently, and the Python projection loop no longer has to handle
ordering.
This preserves the correctness win (old compression roots whose live tip was
touched recently surface correctly) without the O(N) scan, which matters for
users with thousands of sessions.
Adds a regression test pinning the compression-tip case at limit=1 — the
stress case that any bounded-oversample shortcut would get wrong.
Co-authored-by: simbam99 <simbamax99@gmail.com>
- order session_search recent-mode results by last activity instead of session start time
- add an opt-in `order_by_last_active` path to `SessionDB.list_sessions_rich`
- add regression coverage for both the database ordering and recent-mode call path
The PR wired in a detached watcher that respawns manual profile gateways
after they exit. Pair that with a SIGUSR1 graceful drain (same path
systemd/launchd use) so in-flight agent runs finish instead of getting
SIGTERM'd. Fall back to SIGTERM if SIGUSR1 isn't wired or the gateway
doesn't exit within the drain budget — the watcher sees the exit and
relaunches either way.
Tested end-to-end against an orphaned gateway: graceful drain exits in
0.5s and the watcher fires the relaunch command.
When len(messages) <= protect_tail_count and a token budget is set, the
previous formula min(protect_tail_count, len(result) - 1) under-protected
the tail by one, allowing the oldest message to be summarized.
The test fails on the buggy formula (pruned == 1) and passes on the fix
(pruned == 0, tool content preserved verbatim).
Follow-up to #17963. The threaded branch of resolve_plugin_command_result
previously called Event.wait() with no timeout — a hung async plugin
handler would wedge the terminal indefinitely. Cap the wait at 30s and
raise TimeoutError instead. Added a regression test covering the hung
handler path.
The kanban PR (#17805, c86842546) added the `kanban` toolset and
`tools/kanban_tools.py`, but didn't update three pre-existing test
assertions that bake the full toolset/tool inventory:
* `tests/tools/test_registry.py::test_matches_previous_manual_builtin_tool_set`
hard-codes the manual list of builtin tool modules. `tools.kanban_tools`
was missing.
* `tests/test_tui_gateway_server.py::test_load_enabled_toolsets_rejects_disabled_mcp_env`
and `test_load_enabled_toolsets_falls_back_when_tui_env_invalid` both
expect `["memory"]` from `_load_enabled_toolsets()`. With kanban now
auto-recovered by `_get_platform_tools` (its tools live in hermes-cli's
universe but are not in CONFIGURABLE_TOOLSETS), the resolver returns
`["kanban", "memory"]`.
* `tests/hermes_cli/test_tools_config.py::test_get_platform_tools_preserves_explicit_empty_selection`
asserts `set()` for an explicit empty list. The recovery loop now also
surfaces `kanban`. Reframed to assert the contract the test name
describes — no CONFIGURABLE toolset gets re-enabled when the user
explicitly saved an empty list — which stays correct as more
non-configurable platform toolsets are added.
Verified the failures reproduce on clean origin/main (180a7036b) with
`.[all,dev]`-equivalent extras (fastapi, starlette, httpx, pytest-asyncio)
and that all four pass with this commit applied. CI on main itself is
currently red on these tests; this restores green for everyone's PRs.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Signal-cli sends dataMessage wrappers for profile key updates and other
metadata events that have no actual text content. These were reaching the
gateway as msg='' and triggering full agent turns for nothing.
Add early return in _handle_envelope() when both message field is empty/
missing/whitespace AND there are no attachments. Messages with media
attachments but no text still flow through.
- 12 lines added to gateway/platforms/signal.py
- 5 new tests in TestSignalContentlessEnvelope class
The Ink TUI (\`hermes --tui\` + dashboard \`/chat\`) had no wiring for the
background self-improvement review. When the review fired and patched
a skill or saved a memory entry, the change landed but the user had
no visual indication it happened — only the CLI had a print surface
for the '💾 Self-improvement review: …' line.
Changes:
- tui_gateway/server.py: in _init_session, attach
agent.background_review_callback to an _emit('review.summary',
sid, {text}) closure. Wrapped in try/except so agents with locked
attribute slots don't break session startup.
- ui-tui/src/app/createGatewayEventHandler.ts: handle 'review.summary'
by routing ev.payload.text through sys(…), matching the existing
'background.complete' pattern. Empty / whitespace payloads are
ignored so the transcript never gets a blank system line.
- ui-tui/src/gatewayTypes.ts: extend the GatewayEvent discriminated
union with { type: 'review.summary', payload?: { text?: string } }.
Gateway platforms (Telegram, Discord, Slack, …) already route the
review summary via background_review_callback → post-delivery queue
in gateway/run.py, so they pick up the new 'Self-improvement review:'
prefix from the companion run_agent change with no platform edits.
Tests:
- tests/tui_gateway/test_review_summary_callback.py (Python, 2 tests):
_init_session attaches a callback that emits the right event; the
callback path survives agents that can't accept the attribute.
- ui-tui/src/__tests__/createGatewayEventHandler.test.ts (vitest, 2
new cases): review.summary events feed sys(...) with the full text;
empty / missing payloads are no-ops.
- TypeScript type-check passes.
- tui_gateway suite: 64/64 pass.
When the self-improvement background review fires after a turn, it runs
in a bg thread and emits a ' 💾 <summary>' line to announce what it
saved to memory or skills. Two problems made this invisible to users
even when the review successfully modified a skill:
1. The print went through `_cprint` (prompt_toolkit's print_formatted_text)
on a bg thread while the CLI's PromptSession was live. Direct
print_formatted_text races with the input-area redraw and the line
can land behind/above the prompt, scrolled off without the user
seeing it.
2. The message said only '💾 Skill created.' / '💾 Memory updated'
with no indication that the self-improvement loop was the one doing
this. Users who did catch the line couldn't tell the background
review from some other agent action.
Fixes:
- `_cprint` now detects when it's called from a non-app thread with a
running prompt_toolkit Application, and routes through
`run_in_terminal` via `loop.call_soon_threadsafe`. That pauses the
input, prints the line above the prompt, and redraws — the normal
prompt_toolkit contract for bg-thread output. Direct-print fallback
preserved for the no-app / same-thread / import-error paths. Affects
every bg-thread emission, not just the review summary (curator
summaries and auxiliary failure prints benefit too).
- The summary now reads ' 💾 Self-improvement review: <summary>' in
both the CLI and the gateway `background_review_callback` path, so
the origin is unambiguous.
Tests:
- New `tests/cli/test_cprint_bg_thread.py` covers all five routing
branches (no app, app-not-running, cross-thread schedule, same-thread
direct, app-loop-attribute-error, import-error).
- New case in `tests/run_agent/test_background_review.py` asserts the
attributed prefix shows up in both `_safe_print` and
`background_review_callback`.
Live E2E: exercised _cprint from a bg thread inside a real Application
event loop; confirmed get_app_or_none() sees the app, call_soon_threadsafe
schedules run_in_terminal, and the inner _pt_print runs.
Builds on #16855 (@lsdsjy) which fixed DeepSeek v4 reasoning_content
replay via model_extra fallback + capturing tool_calls at method entry.
Kimi / Moonshot thinking mode enforces the same echo-back contract and
hits the same 400 when a tool-call turn is persisted without
reasoning_content.
- _build_assistant_message: pad branch now uses _needs_thinking_reasoning_pad()
(DeepSeek OR Kimi) instead of _needs_deepseek_tool_reasoning() alone.
- Extract _needs_thinking_reasoning_pad() and reuse it in
_copy_reasoning_content_for_api so both sites share one predicate.
- tests/run_agent/test_deepseek_reasoning_content_echo.py: add
TestBuildAssistantMessagePadsStrictProviders parametrized over DeepSeek
(attr=None, attr-absent), Kimi (attr=None), Moonshot (via base_url),
and an OpenRouter negative control that must NOT pad. Proven to fail
2/5 cases on Kimi/Moonshot without this change.
- scripts/release.py: add AUTHOR_MAP entries for lsdsjy and season179.
Refs #17400.
Co-authored-by: season179 <season.saw@gmail.com>
Alongside the existing 'least recently used' section, surface two more
rankings so users can see which of their agent-created skills actually
get exercised:
- 'most used (top 5)' — sorted by use_count descending. Hidden when every
skill has use_count=0 (noise suppression on fresh installs).
- 'least used (top 5)' — sorted by use_count ascending. Always shown
when the catalog is non-empty.
use_count started tracking real agent skill activation in PR #17932
(bump_use wired into skill_view tool + slash invocation + --skill
preload), so these rankings are now meaningful.
Tests: 3 new in tests/hermes_cli/test_curator_status.py — happy path
with mixed use_counts, zero-use suppression of the most-used section,
and the no-skills clean-empty case.
Treat skill views and edits as activity when curator reports and applies lifecycle transitions, so recently loaded or patched skills are not displayed or transitioned as never used.\n\nAdds regression tests for activity derivation, automatic transitions, and CLI status output.
restore_skill() in tools/skill_usage.py used archive_root.iterdir(), which
only walked the top level of .archive/. Skills archived under nested layouts
(e.g. .archive/openclaw-imports/<skill>/ from older archive paths or
external imports) were invisible to both the exact-match and prefix-match
candidate scans, surfacing as a misleading "skill '<name>' not found in
archive" error even though the directory existed on disk.
Switch both candidate scans to archive_root.rglob('*') so the lookup
descends into category subdirectories.
Fixes#17942
* fix(curator): split 'archived' into consolidated vs pruned in run reports
Users who watched a curator run saw skills like 'anthropic-api' listed
under 'Skills archived' and interpreted that as pruning — but the curator
had actually absorbed those skills into a new umbrella (e.g. 'llm-providers')
during the same run. The directory gets archived for safety (all removals
are recoverable), but the content still lives under a different name.
Users then 'restored' what they thought were deleted skills and ended up
with confusingly duplicated skillsets (old-name + absorbed-inside-umbrella).
Classify removed skills using this run's skill_manage tool calls:
- consolidated: content absorbed into a surviving/newly-created skill
(evidenced by a skill_manage write_file/patch/create/edit whose target
is a different skill AND whose file_path/content references the
removed skill's name)
- pruned: archived without consolidation evidence (truly stale)
REPORT.md now shows two distinct sections:
- 'Consolidated into umbrella skills' — with `removed → merged into umbrella`
- 'Pruned — archived for staleness' — pure staleness archives
run.json schema additions (backward compatible):
- counts.consolidated_this_run, counts.pruned_this_run
- consolidated: [{name, into, evidence}, ...]
- pruned: [names]
- archived: retained as the union for backward compat
Also: relabel the auto-transitions 'archived' counter to 'archived (no
LLM, pure time-based staleness)' so it's clearly distinct from LLM-pass
archives.
Tests: 9 new tests in test_curator_classification.py covering consolidation
evidence parsing (write_file/patch/create), hyphen/underscore name variants,
self-reference rejection, destination-must-exist, mixed runs, and
malformed-JSON fallback safety. Existing test_report_md_is_human_readable
updated to cover the new section names.
E2E: isolated HERMES_HOME, realistic 3-skill run, REPORT.md verified
end-to-end.
* feat(curator): hybrid model-declared + heuristic classification
Extend the consolidated-vs-pruned split with LLM-authored intent:
1. Curator prompt now requires a structured YAML block at the end of the
final response (consolidations / prunings with short rationale).
2. _parse_structured_summary() extracts it tolerantly — missing block,
malformed YAML, partial lists all fall back to heuristic cleanly.
3. _reconcile_classification() merges model intent with the tool-call
heuristic:
- Model wins on rationale when its umbrella exists post-run
- Model hallucination (umbrella doesn't exist) is downgraded to the
heuristic's finding, or pruned if there's no evidence either
- Heuristic catches model omission — consolidations the model
enumerated tools for but forgot to list get surfaced with a
'(detected via tool-call audit)' tag
4. REPORT.md now shows per-row rationale alongside 'removed → umbrella'
and flags audit-only rows so the user knows why no reason is shown.
Backward compat: run.json's 'archived' field (union) is preserved.
'pruned' is now a list of dicts with {name, source, reason};
'pruned_names' is the flat-name list for legacy consumers.
Tests: 15 new covering YAML parse edge cases (malformed, empty lists,
bare-string entries, missing fields), reconciler rules (model wins,
hallucination fallback, heuristic catches omission, prune with reason),
and an end-to-end report-render test with all four paths exercised.
Belt-and-suspenders on top of @briandevans' #17758 fix. The in-band
drain hand-off (await->create_task + session-guard preservation)
changed cleanup semantics in three places that the original PR
reasoned about but didn't test directly. Pin each invariant so a
future refactor can't silently regress them:
1. Normal single-message path still releases _active_sessions[sk] and
_session_tasks[sk] through end-of-finally. The #17758 follow-up
moved _release_session_guard under
if current_task is self._session_tasks.get(session_key)
For the 99%-common case current_task IS the stored task, so the
guard must still fire. Test would fail if the conditional were
ever tightened in a way that dropped the normal path.
2. Drain-task cancellation releases the session. If the drain task
spawned by the in-band hand-off is cancelled mid-handler (e.g.
/stop fired while draining a follow-up), its own finally must
fire _release_session_guard. Without this a cancel would leave
the session permanently pinned busy.
3. Late-arrival drain still spawns when no in-band drain preceded
it. Pre-existing path, but the #17758 follow-up added a
re-queue branch that only fires when ownership was already
handed off. When no handoff happened the else branch must still
spawn a fresh drain task — otherwise a message arriving during
stop_typing gets silently dropped.
All three tests pass against current main. Zero production code
changes.
The #1630 fix introduced a blanket ``agent_failed_early`` transcript skip
to prevent context-overflow sessions from looping. That guard also
triggers for unrelated transient failures (429 rate limits, read
timeouts, connection resets, provider 5xx) which have nothing to do with
session size — and it silently drops the user's message, so the agent
has no memory of the last turn on retry.
Split the failure classification in ``GatewayRunner._run_agent``:
* Context-overflow (``compression_exhausted`` flag, explicit
context-length phrases, or generic 400 with a long history) → keep
the existing skip, preserving the #1630/#9893 fix.
* Anything else that failed → persist just the user message so the
conversation survives a retry.
Use specific multi-word phrases (``context length``, ``token limit``,
``prompt is too long``, etc.) to match ``run_agent.py``'s own
classifier; bare ``exceed`` false-positively flagged "rate limit
exceeded" as context overflow.
Covered by new tests in ``tests/gateway/test_7100_transient_failure_transcript.py``
and the existing #1630 suite still passes.
Existing test_tar_pipe_commands asserted the literal substring
'tar xf - -C /' in ssh_str, which is no longer present after the
#17767 fix adds --no-overwrite-dir between 'tar xf -' and '-C /'.
Split the one substring check into three independent assertions for
the tar stdin mode, the new --no-overwrite-dir flag (regression guard
for #17767), and the extract target.
_set_nested unconditionally replaced any non-dict value with an empty
dict when walking the dotted path, which silently destroyed list-typed
config nodes the moment someone set a value with a numeric index
(e.g. 'hermes config set custom_providers.0.api_key NEW'). Any sibling
entries and any fields inside the targeted entry that the user didn't
write were lost.
Fix:
- _set_nested now detects list nodes and navigates by numeric index,
and preserves both dicts AND lists at intermediate positions (scalars
are still replaced so bare-scalar -> nested overrides keep working).
- set_config_value drops its duplicated navigation logic and calls
_set_nested instead -- single source of truth for the rules.
Regression tests (tests/hermes_cli/test_set_config_value.py):
- test_indexed_set_preserves_sibling_list_entries -- exact #17876 repro
- test_indexed_set_preserves_non_targeted_fields -- inner-dict fields survive
- test_deeper_nesting_through_list -- dict -> list -> dict -> scalar path
35/35 existing + new tests pass.
E2E-verified with the issue's repro against a real on-disk config.yaml --
list stays a list, entry 0 updated, entry 1 intact.
Closes#17876
Long-lived Gateway processes were sending duplicate tool names to
providers that enforce uniqueness:
- DeepSeek: 'Tool names must be unique.'
- Xiaomi MiMo: 'tools contains duplicate names: lcm_expand'
- Moonshot/Kimi: 'function name lcm_grep is duplicated'
TUI was unaffected because TUI runs with quiet_mode=False and skips the
cache entirely.
Root cause (two layered bugs)
- model_tools.get_tool_definitions(quiet_mode=True) memoizes its result
in _tool_defs_cache. The cache-hit path returned list(cached) (safe),
but the FIRST uncached call stored and returned the SAME object.
run_agent.py mutates self.tools (memory + LCM context-engine schemas)
in-place, so the very first agent init in a Gateway process
poisoned the cache, and every subsequent init appended LCM schemas
again on top of the already-polluted list.
- run_agent.py's context-engine injection (lcm_grep / lcm_describe /
lcm_expand) had no dedup, unlike the memory-tools injection right
above it which already skips already-present names.
Fix (defense in depth, per the issue's suggested fix)
- model_tools.get_tool_definitions: on the uncached branch, cache the
computed list but return list(result) to the caller. Same pattern as
the cache-hit path.
- run_agent.py: build _existing_tool_names from self.tools and skip
schemas whose names are already present, mirroring the memory-tools
block. This also defends against plugin paths that may register the
same schemas via ctx.register_tool().
Tests (tests/test_get_tool_definitions_cache_isolation.py)
- test_first_uncached_call_returns_fresh_list \u2014 pins the fix; without
it, first-call alias caused all the symptoms.
- test_cache_hit_returns_fresh_list \u2014 pre-existing behavior stays.
- test_caller_mutation_does_not_poison_cache \u2014 simulates run_agent
appending lcm_grep / lcm_expand to the returned list and asserts the
next call doesn't see them.
- test_repeated_caller_mutation_does_not_accumulate \u2014 reproduces the
long-lived Gateway accumulation pattern across 5 agent inits.
- test_non_quiet_mode_does_not_use_cache \u2014 sanity, explains why TUI
was fine.
5/5 pass on the new file; 23/23 still pass on tests/test_model_tools.py.
When a user sets model.context_length in config.yaml, the value was only
used for Hermes' internal compression decisions (context_compressor) but
NOT for Ollama's num_ctx parameter. Ollama auto-detects context from GGUF
metadata (often 256K+) and allocates that much VRAM regardless of the
user's config — causing OOM on smaller GPUs like the P100 (16GB).
Root cause: two separate context values existed independently:
- context_compressor.context_length = config value (e.g. 65536) ✓
- _ollama_num_ctx = GGUF metadata value (e.g. 256000) ✗ ignored config
Changes:
1. Cap Ollama num_ctx to config context_length (run_agent.py)
When model.context_length is explicitly set and no explicit
ollama_num_ctx override exists, cap the auto-detected GGUF value
to the user's context_length. This is the core fix — it prevents
Ollama from allocating more VRAM than the user budgeted.
2. Pass config_context_length through all secondary call sites
Several paths called get_model_context_length() without the config
override, falling through to the 256K default fallback:
- cli.py: @-reference expansion and /model switch display
- gateway/run.py: @-reference expansion and /model switch display
- tui_gateway/server.py: @-reference expansion
- hermes_cli/model_switch.py: resolve_display_context_length()
3. Normalize root-level context_length in config (hermes_cli/config.py)
_normalize_root_model_keys() now migrates root-level context_length
into the model section, matching existing behavior for provider and
base_url. Users who wrote `context_length: 65536` at the YAML root
instead of under `model:` had it silently ignored.
4. Fix misleading comments (agent/model_metadata.py)
DEFAULT_FALLBACK_CONTEXT is 256K (CONTEXT_PROBE_TIERS[0]), not 128K
as two comments stated.
Tests: 3 new tests for root-level context_length normalization.
All existing context_length tests pass (96 tests).
The busy-session handler (_handle_active_session_busy_message) bypassed the
authorization gate that the cold path enforces via _is_user_authorized(). In
shared-thread contexts (Slack threads, Telegram forum topics, Discord threads)
where thread_sessions_per_user=False (the default), all participants share one
session_key. An unauthorized user posting in the same thread as an authorized
user would hit the active-session branch, skip the auth check, and have their
text merged into _pending_messages or injected via agent.interrupt().
This commit adds the same _is_user_authorized() check at the top of the busy
handler, before any message queuing, steering, or interrupt logic. Unauthorized
messages are silently dropped (return True) with a warning log — matching the
cold-path behavior.
Affected platforms: Slack, Telegram, Discord, any adapter with shared-session
thread contexts.
Closes#17775
The `gemini` provider also serves Gemma (e.g. `gemma-4-31b-it`) and
historically other Google models like PaLM. Those reject
`extra_body.thinking_config` with HTTP 400:
Unknown name "thinking_config": Cannot find field
`_build_gemini_thinking_config()` was unconditionally producing a
config dict for any model on the `gemini` / `google-gemini-cli`
provider, which `ChatCompletionsTransport.build_kwargs` then dropped
into `extra_body["thinking_config"]`. The result: every chat turn for
Gemma users on the gemini provider blew up at the API edge.
The fix is the same shape Hermes already uses for the Gemini-2.5 vs
Gemini-3 family clamping: normalise the model id, strip an
`OpenRouter`-style `google/` prefix, and short-circuit early when the
result doesn't start with `gemini`. We return `None` rather than
`{"includeThoughts": False}`, because the API rejects the field name
itself — even the polite "off" form trips the same 400.
Three regression tests cover Gemma with reasoning enabled, Gemma with
reasoning disabled, and the `google/gemma-…` OpenRouter-style id; the
existing Gemini-2.5 / Gemini-3 / `google/gemini-…` cases keep passing
because the Gemini guard fires after the prefix strip.
Fixes#17426
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Ports PR #17888's send_multiple_images ABC to every gateway platform that
has a native multi-attachment API, so images arrive as a single bundled
message instead of N separate ones.
Native overrides:
- Telegram: send_media_group (10 photos per album, chunks over); animated
GIFs peeled off and routed through send_animation (albums don't support
animations)
- Discord: channel.send(files=[...]) (10 attachments per message, chunks
over); URL images downloaded into BytesIO so they render inline; forum
channels use create_thread with files=[...]
- Slack: files_upload_v2(file_uploads=[...]) (10 per call, chunks over);
respects thread_ts; records thread participation
- Mattermost: single post with file_ids list (5 per post — Mattermost cap,
chunks over)
- Email: single SMTP message with multiple MIME attachments (no chunk cap,
SMTP size governs); remote URLs remain linked in body (parity with
existing send_image)
All platforms fall back to the base per-image loop on any failure, so a
single bad image in a batch never loses the rest.
Matrix, WhatsApp, and single-attachment platforms (BlueBubbles, Feishu,
WeCom, WeChat, DingTalk) continue to use the base default loop — their
server APIs only accept one attachment per message anyway.
Tests: adds tests/gateway/test_send_multiple_images.py with 19 targeted
tests covering base default loop, chunking, animation peel-off, fallback
paths, and empty-batch no-ops across all five new overrides.
Co-authored-by: Maxence Groine <maxence@groine.fr>
Adds a new `send_multiple_images` method to the ``BasePlatformAdapter``
that implements the default "One image per message" loop and allows for
platform-specific overriding.
Implements such an override for the Signal adapter, batching images
and trying (best-effort) to work around rate-limits for voluminous
batches using a specific scheduler.
Also implements batching + rate-limit handling in the `send_message`
tool.
New tests added for the Signal adapter, its rate-limit scheduler and the
`send_message` tool
Merge resolved conflicts in web/src/{i18n/{en,zh,types}.ts,lib/api.ts}
by keeping both this branch's `profiles` additions and upstream's new
`models` page additions.
Copilot review feedback:
- Implement POST /api/profiles/{name}/open-terminal endpoint (already
present); align Windows branch to `cmd.exe /c start "" <cmd>` so it
matches the new test and spawns a fresh window instead of /k reusing
the parent console.
- Move backslash escaping out of the macOS AppleScript f-string
expression (Python <3.12 disallows backslashes inside f-string
expression parts).
- Patch `_get_wrapper_dir` via monkeypatch in
test_profiles_create_creates_wrapper_alias_when_safe so the test no
longer writes to the real `~/.local/bin`.
- Extend test_dashboard_browser_safe_imports to scan `.ts` files in
addition to `.tsx`.
- Switch upstream's new ModelsPage.tsx away from the `@nous-research/ui`
root barrel onto per-component subpaths to satisfy the stricter scan.
- Fix NouiTypography `leading-1.4` -> `leading-[1.4]` so Tailwind
actually emits the line-height for the `sm` variant.
- Guard ProfilesPage.openSoulEditor against out-of-order responses by
tracking the latest requested profile via a ref.
- Replace ProfilesPage's hand-rolled setup command with a fetch to
`/api/profiles/{name}/setup-command` so the copied command always
matches what the backend would actually run (handles wrapper-alias
collisions and reserved names correctly).
- Wire SOUL.md textarea label `htmlFor` -> textarea `id` so screen
readers and clicking the label work as expected.
The sandbox-side `_call()` in both the UDS and file-based transports was
not thread-safe, so scripts that call tools from multiple threads (e.g.
`ThreadPoolExecutor` over `terminal()`) inside a single `execute_code`
run could silently receive each other's responses.
Root cause:
* UDS transport — a single module-level `_sock` was shared across all
threads; the newline-framed protocol has no request-id; and the
server-side RPC loop handles one connection serially. With concurrent
callers, each thread would `sendall()` then race to `recv()` the next
newline-terminated response from the shared buffer, so responses got
delivered to the wrong caller.
* File transport — `_seq += 1` is a non-atomic read-modify-write, so
two threads could allocate the same sequence number and clobber each
other's request/response files.
Fix: guard `_call()` with a `threading.Lock` in the UDS case (covering
send+recv), and guard `_seq` allocation with a lock in the file case.
No protocol change.
Regression tests cover both the generated-source level (lock is present
and used) and an end-to-end concurrency test: running a sandboxed
ThreadPoolExecutor of 10 `terminal()` calls against a slow mock
dispatcher, asserting every caller sees its own tagged response. The
test fails without the fix (10/10 mismatched, matching real-world
repro) and passes with it.
The v11→v12 migrate_config step writes the API mode for every entry
under the new transport: field (per the v12+ schema in
_normalize_custom_provider_entry). _get_named_custom_provider
read the legacy api_mode: spelling only, so for every migrated
config the lookup returned None for the api mode.
Downstream, _resolve_named_custom_runtime then falls back through
custom_provider.get("api_mode") or _detect_api_mode_for_url(base_url)
or "chat_completions". For loopback URLs (proxies, local servers)
or unknown hostnames, the URL detector returns None and the resolver
silently downgrades the configured codex_responses /
anthropic_messages transport to chat_completions. Requests
get sent to /v1/chat/completions instead of /v1/responses or
/v1/messages and the provider 404s — or worse, returns a usable
chat_completions response while skipping the model's reasoning /
caching surface.
Fix: read both field names — entry.get("api_mode") or
entry.get("transport") — at the two match-by-key + match-by-name
branches in _get_named_custom_provider. The runtime normaliser
_normalize_custom_provider_entry already accepts both spellings;
this lifts the same compat into the direct-dict reader so v12+
configs work without going through the shim.
Adds three regression tests under
tests/hermes_cli/test_user_providers_model_switch.py:
- transport field is read on the match-by-key branch
- legacy api_mode spelling still works for hand-edited configs
- transport is read on the match-by-display-name branch
run_job() ignored the result's `failed=True` / `completed=False` flags
that agent.run_conversation populates on API exhaustion, mid-run
interrupts, and model aborts. Because final_response on those paths is
often a non-empty error string ("API call failed after 3 retries:
Request timed out."), the existing empty-response soft-fail in
_process_job did not trip either: the error text was delivered as if it
were the agent's reply and last_status was set to "ok" with no error
notification. Detect those flags right after the dict-shape guard and
raise so the existing except handler builds the proper failure tuple,
preserving the agent's error message via result["error"].
Adds a parametrized regression covering: API-retry-exhausted with error
text in final_response, completed=False with no final_response,
completed=False without an explicit failed flag, and the partial-reply
plus failed=True case. Plus a guard that a normal completed=True success
result is still treated as success.
Fixes#17855
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
When the in-band pending-message drain spawns a fresh task and
transfers ownership via _session_tasks[session_key] = drain_task,
the original task still unwinds through the finally block. The
drain task picks up the same interrupt_event in its own
_process_message_background entry, so an unconditional
_release_session_guard(session_key, guard=interrupt_event) at the
end of the finally matches and deletes _active_sessions[session_key]
while the drain task is still pending its first await.
A concurrent inbound message arriving in that handoff window passes
the Level-1 guard (no entry exists) and spawns a second
_process_message_background for the same session — two agents on
one session_key, duplicate responses, duplicate tool calls.
Fix: only call _release_session_guard when the current task still
owns _session_tasks[session_key]. When ownership has been
transferred to a drain task, leave _active_sessions populated; the
drain task's own lifecycle releases it. This mirrors the
late-arrival drain path in the same finally block, which already
leaves both entries alone after handing off.
Also reorder stdlib imports in the new regression test file to
match the gateway test convention (stdlib before third-party).
Regression test: capture _active_sessions[sk] identity at every
handler entry across a 2-step in-band drain chain and assert the
guard Event identity stays the same. Pre-fix, the original task's
finally deletes the entry, the drain task falls through to the
`or asyncio.Event()` branch, and a fresh Event is installed —
identity diverges. Post-fix, the entry is preserved and the drain
task reuses the original Event.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`_process_message_background` finished a turn, found a queued
follow-up, and drained it via `await
self._process_message_background(pending_event, session_key)`. Each
chained follow-up added a frame to the call stack instead of starting
fresh. Under sustained pending-queue activity (e.g. a user sending
follow-ups faster than the agent finishes turns) the C stack would
exhaust at ~2000 nested frames and SIGSEGV the process.
Mirror the late-arrival drain pattern that already exists in the same
function: spawn a new `asyncio.create_task(...)` for the pending event
and return so the current frame can unwind. The new task takes
ownership via `_session_tasks[session_key]`.
The late-arrival drain in `finally` could now race with the in-band
drain across the `await typing_task` / `await stop_typing` window, so
add a guard: if `_session_tasks[session_key]` is no longer the current
task, an in-band drain already spawned a follow-up task — re-queue the
late-arrival event so that task picks it up after its current event,
instead of spawning a second concurrent task for the same session_key.
Regression test (`test_pending_drain_no_recursion.py`) chains 12
follow-ups and asserts the recorded
`_process_message_background` stack depth stays bounded at handler
entry. Pre-fix: depths grow linearly `[1,2,3,…,12]`. Post-fix: all
depths are `1`.
`test_duplicate_reply_suppression::test_stale_response_suppressed_when_interrupted`
called `_process_message_background` directly and implicitly relied on
the old recursive `await` semantic — updated to wait for the spawned
drain task before checking the sent list.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Piper (OHF-Voice/piper1-gpl) is a fast, local neural TTS engine from the
Home Assistant project that supports 44 languages with zero API keys.
Adds it as a native built-in provider alongside edge/neutts/kittentts,
installable via 'hermes tools' with one keystroke.
What ships:
- New 'piper' built-in provider in tools/tts_tool.py
- Lazy import via _import_piper()
- Module-level voice cache keyed on (model_path, use_cuda) so switching
voices doesn't invalidate older cached voices
- _resolve_piper_voice_path() accepts either an absolute .onnx path or a
voice name (auto-downloaded on first use via 'python -m
piper.download_voices --download-dir <cache>')
- Voice cache at ~/.hermes/cache/piper-voices/ (profile-aware via
get_hermes_dir)
- Optional SynthesisConfig knobs: length_scale, noise_scale,
noise_w_scale, volume, normalize_audio, use_cuda — passed through
only when configured, so older piper-tts versions aren't broken
- WAV output then ffmpeg conversion path (same as neutts/kittentts) so
Telegram voice bubbles work when ffmpeg is present
- Piper added to BUILTIN_TTS_PROVIDERS so a user's
tts.providers.piper.command cannot shadow the native provider
(regression test included)
- 'hermes tools' wizard entry
- Piper appears under Voice and TTS as local free, with
'pip install piper-tts' auto-install via post_setup handler
- Prints voice-catalog URL and default-voice info after install
- config.yaml defaults
- tts.piper.voice defaults to en_US-lessac-medium
- Commented advanced knobs for discoverability
- Docs
- New 'Piper (local, 44 languages)' section in features/tts.md
explaining install path, voice switching, pre-downloaded voices,
and advanced knobs
- Piper listed in the ten-provider table and ffmpeg table
- Custom-command-providers section updated to drop the Piper example
(now native) and add a piper-custom example for users with their own
trained .onnx models
- overview.md bumps provider count to ten
- Tests (tests/tools/test_tts_piper.py, 16 tests)
- Registration (BUILTIN_TTS_PROVIDERS, PROVIDER_MAX_TEXT_LENGTH)
- _resolve_piper_voice_path across every branch: direct .onnx path,
cached voice name, fresh download with correct CLI args, download
failure, successful-exit-but-missing-files, empty voice to default
- _generate_piper_tts: loads voice once, reuses cache, voice-name
download wiring, advanced knobs flow through SynthesisConfig
- text_to_speech_tool end-to-end dispatch and missing-package error
- check_tts_requirements: piper availability toggles the return value
- Regression guard: piper cannot be shadowed by a command provider
with the same name
- Pre-existing test_tts_mistral test broadened to mock the new
piper/kittentts/command-provider checks (otherwise it false-passes
when piper is installed in the test venv)
E2E verification (live):
Actual pip install piper-tts, config piper + en_US-lessac-low,
text_to_speech_tool call, voice auto-downloaded from HuggingFace,
WAV synthesized, ffmpeg-converted to Ogg/Opus. Second call hits the
cache (~60ms). Cache dir populated with .onnx and .onnx.json.
This caught a real bug during development: the first pass used '-d' as
the download-dir flag; the actual piper.download_voices CLI wants
'--download-dir'. Fixed before PR opened.
Six tests in this file failed in CI (-n auto) after #17832 landed because
other tests on the same xdist worker reload hermes_cli.main:
tests/hermes_cli/test_env_loader.py:85-86
sys.modules.pop('hermes_cli.main', None)
importlib.import_module('hermes_cli.main')
tests/hermes_cli/test_skills_subparser.py:24-25
del sys.modules['hermes_cli.main']
When either ran first on a worker, our top-of-file
'from hermes_cli.main import _kill_stale_dashboard_processes' captured a
stale function object whose __globals__ points at the old module dict.
patch('hermes_cli.main._find_stale_dashboard_pids', ...) then patched the
new module, but the stale function resolved the dependency via its stale
__globals__, so every patch became a no-op: pids=[] → early return → no
signals, no output, assertions failed.
Fix: add an autouse fixture that rebinds the three module-level names to
whatever is currently live in sys.modules['hermes_cli.main'] before each
test runs. The pollutants in the other two files are load-bearing for
their own tests, so fixing it on the consumer side is correct.
Repro: pytest tests/hermes_cli/test_env_loader.py tests/hermes_cli/test_update_stale_dashboard.py
Voscko reported curator.auxiliary.provider/model was advertised in the
docs but ignored — the review fork read only model.provider/default. The
narrow fix would wire the one-off key through, but that leaves curator
as a parallel system: not in `hermes model` → auxiliary picker, not in
the dashboard Models tab, missing per-task base_url/api_key/timeout/
extra_body.
Unify curator with the rest of the aux task system so `hermes model`
and the dashboard configure it like every other aux task.
Four sources of truth updated:
- hermes_cli/config.py — add 'curator' slot to DEFAULT_CONFIG.auxiliary
(timeout=600 since reviews run long), drop the one-off curator.auxiliary
block from DEFAULT_CONFIG.curator.
- hermes_cli/main.py — add ('curator', 'Curator', 'skill-usage review pass')
to _AUX_TASKS so the CLI picker offers it.
- hermes_cli/web_server.py — add 'curator' to _AUX_TASK_SLOTS so the
dashboard REST endpoint accepts it.
- web/src/pages/ModelsPage.tsx — add Curator entry so the dashboard
Models tab renders the task.
agent/curator.py _resolve_review_model() now reads auxiliary.curator
first (canonical), falls back to legacy curator.auxiliary (with an info
log asking users to migrate), then falls back to the main chat model.
Pre-unification users keep working.
Docs updated: docs/user-guide/features/curator.md now points at
`hermes model` → auxiliary → Curator and the dashboard Models tab.
Tests: 6 unit tests on _resolve_review_model (auto default, canonical
slot honored, partial override fallback, legacy fallback with
deprecation log assertion, new-wins-over-legacy, empty-config safety)
plus a cross-registry test that curator is wired into all four sources
of truth. test_aux_tasks_keys_all_exist_in_default_config already
covers the DEFAULT_CONFIG ↔ _AUX_TASKS invariant.
Reported by Voscko on Discord.
UserMessageChunk and AgentMessageChunk do not have a message_id field
in the ACP schema. Passing it silently dropped the kwarg (pydantic
does not raise on unknown init kwargs here) and the subsequent test
assertions on .message_id raised AttributeError. Strip the dead
plumbing (uuid import, message_id= kwarg on both chunk types, unused
session_id/index parameters) and remove the matching .message_id
asserts from the test.
Adds a deterministic pre-check on top of htsh's exception-based fallback:
before calling /content/abstract or /content/overview on a non-pseudo URI,
probe /api/v1/fs/stat. If the server says the URI is a file, route straight
to /content/read instead of eating a failing 500 round-trip.
This is the same idea pty819 and chennest independently landed in PRs
#12757 and #12937 — merged here on top of htsh's broader fix so we keep
pseudo-URI normalization and v0.3.3 browse-shape handling while avoiding
the slow exception path on servers that return a raised 500 every time.
The exception fallback from #5886 stays in place for environments where
fs/stat is unavailable or returns an unfamiliar shape.
Also credits pty819, chennest, and htsh in AUTHOR_MAP so future release
notes attribute them correctly.
OpenViking returns 500 for /content/abstract and /content/overview when URI points to mem_*.md files.
Add resilient fallback to /content/read for non-pseudo summary file URIs while preserving pseudo summary normalization.
Also add regression tests for fallback behavior.
`hermes dashboard` is a long-lived foreground server that users often
start and forget about, sometimes in a shell they've since closed. We
didn't have a way to stop it — users had to find the PID manually.
Adds two lifecycle flags that reuse the same detection + termination
path the post-`hermes update` cleanup (PR #17832) uses:
hermes dashboard --status
List running hermes dashboard processes with PID + cmdline.
Exit 0, informational.
hermes dashboard --stop
Terminate all running dashboards (3s grace then force-kill survivors).
Exit 0 if none remain, 1 if any couldn't be stopped.
Windows uses `taskkill /F` as before.
Both flags short-circuit before any fastapi/uvicorn import so they work
even on installations where the dashboard extras aren't installed —
useful when you're cleaning up after uninstalling.
The kill helper gained an optional `reason=...` param so the output
reads "(requested via --stop)" instead of the post-update-specific
"running backend no longer matches the updated frontend" wording.
E2E: `hermes dashboard --status` with nothing running prints the
empty message; with a fake `hermes dashboard ...` cmdline spawned via
`exec -a`, `--status` lists it, `--stop` terminates it (exit -15),
and a follow-up `--status` returns empty.
Reshape of PR #17211 (@versun). Lets users wire any local or external
TTS CLI into Hermes without adding engine-specific Python code. Users
declare any number of named providers in config.yaml and switch between
them with tts.provider: <name>, alongside the built-ins (edge, openai,
elevenlabs, …).
Config shape:
tts:
provider: piper-en
providers:
piper-en:
type: command
command: 'piper -m ~/model.onnx -f {output_path} < {input_path}'
output_format: wav
Placeholders: {input_path}, {text_path}, {output_path}, {format},
{voice}, {model}, {speed}. Use {{ / }} for literal braces.
Key behavior:
- Built-in provider names always win — a tts.providers.openai entry
cannot shadow the native OpenAI provider.
- type: command is the default when command: is set.
- Placeholder values are shell-quote-aware (bare / single / double
context), so paths with spaces and shell metacharacters are safe.
- Default delivery is a regular audio attachment. voice_compatible: true
opts in to Telegram voice-bubble delivery via ffmpeg Opus conversion.
- Command failures (non-zero exit, timeout, empty output) surface to
the agent with stderr/stdout included so you can debug from chat.
- Process-tree kill on timeout (Unix killpg, Windows taskkill /T).
- max_text_length defaults to 5000 for command providers; override
under tts.providers.<name>.max_text_length.
Tests: tests/tools/test_tts_command_providers.py — 42 new tests cover
provider resolution, shell-quote context, placeholder rendering with
injection payloads, timeout, non-zero exit, empty output, voice_compatible
opt-in, and end-to-end dispatch through text_to_speech_tool. All 88
pre-existing TTS tests still pass.
Docs: new "Custom command providers" section in
website/docs/user-guide/features/tts.md with three worked examples
(Piper, VoxCPM, MLX-Kokoro), placeholder reference, optional keys,
behavior notes, and security caveat.
E2E-verified live: isolated HERMES_HOME, command provider declared in
config.yaml, text_to_speech_tool dispatches through the registered
shell command and the output file is produced as expected.
Co-authored-by: Versun <me+github7604@versun.org>
`hermes update` previously just printed a warning when it detected a
running `hermes dashboard` process from the previous version, telling
the user to kill and restart it themselves. In practice dashboards get
started and forgotten, so the warning was routinely ignored and users
ended up with a silent frontend/backend mismatch (new JS bundle served
against the old in-memory Python backend, e.g. new auth headers the old
code doesn't recognise → every API call 401s).
The dashboard has no service manager, no PID file, and we don't record
the original launch args (--host, --port, --insecure, --tui, --no-open)
so we can't auto-restart it. But we CAN stop it, which is what the
user wants — the failure mode when the stale process is left alive is
worse than the dashboard just being down.
- POSIX: SIGTERM, poll for ~3s, SIGKILL any survivors.
- Windows: `taskkill /PID <pid> /F`.
- Print each PID's outcome plus a one-line restart hint.
- Detection logic is unchanged (same ps / wmic scan, same guards
against the `pgrep -f` greedy-match trap from #16872 and the
#17049 wmic UnicodeDecodeError fix).
Also split the old monolithic `_warn_stale_dashboard_processes` into
`_find_stale_dashboard_pids` (scan) + `_kill_stale_dashboard_processes`
(kill), keeping the old name as an alias so any external callers still
work.
E2E verified: spawned a fake `hermes dashboard` cmdline via
`exec -a 'hermes dashboard …' sleep 300`, ran
`_kill_stale_dashboard_processes()`, confirmed SIGTERM exit (-15)
and that a post-scan returns an empty PID list.
Three narrow fixes targeting the remaining red checks after #17828:
1. ui-tui/src/app/slash/commands/ops.ts (Docker Build):
/reload-mcp's local params type annotated session_id: string
while ctx.sid is string | null. Widen to string | null —
matches every other rpc call site and the test harness which passes
{ session_id: null }. Fixes TS2322 on line 86. The rpc signature
itself is Record<string, unknown>, so this is purely a local
typing fix, no behavioral change.
2. tests/plugins/test_achievements_plugin.py (13 cascading test failures):
_install_fake_session_db did a raw sys.modules['hermes_state'] =
fake_module without restoration, leaking the fake across xdist
worker boundaries. Downstream tests doing from hermes_state import
SessionDB got a module whose SessionDB was lambda: fake_db
— 6 test_hermes_state.py tests failed with AttributeError: 'function'
object has no attribute '_sanitize_fts5_query' / _contains_cjk,
and 7 test_860_dedup.py tests failed with TypeError: got unexpected
keyword argument 'db_path' (real code calls SessionDB(db_path=...)).
Fix: stash monkeypatch on the plugin_api module object in the
fixture, and have the helper do monkeypatch.setitem(sys.modules,
'hermes_state', fake_module) for auto-restoration at test teardown.
3. tests/hermes_cli/test_web_server.py (WS race):
TestPtyWebSocket::test_pub_broadcasts_to_events_subscribers hit the
30s test timeout on CI. websocket_connect returns after
ws.accept() — but /api/events registers the subscriber in
_event_channels on the NEXT await (inside _event_lock). A
publish immediately after connect could race ahead of registration
and be dropped, and the subsequent receive_text() blocked until
SIGALRM killed the test. Fix: poll _event_channels after the
subscriber connects, before publishing.
Validation:
scripts/run_tests.sh tests/plugins/test_achievements_plugin.py
tests/run_agent/test_860_dedup.py
tests/test_hermes_state.py
tests/hermes_cli/test_web_server.py 338 passed
cd ui-tui && npm run type-check clean
cd ui-tui && npm run build clean
Remaining red checks are pure infra (Nix ubuntu hits
TwirpErrorResponse ResourceExhausted on the GH Actions cache API; Nix
macos bounces between npm build openssl-legacy and cache rate-limits)
and cannot be fixed in the codebase.
Extracted from PR #17211 (@versun) so it can land independently of the
local_command TTS provider redesign.
- Add should_send_media_as_audio(platform, ext, is_voice) in
gateway/platforms/base.py; single source of truth for audio routing.
- Add .flac to recognized audio extensions (MEDIA regex, weixin audio
set, send_message audio set).
- Telegram send_voice() now falls back to send_document for formats
Telegram's Bot API can't play natively (.wav, .flac, ...) instead of
raising; MP3/M4A still go to sendAudio, Opus/OGG still go to sendVoice.
- Route _send_telegram() in send_message_tool through a narrower
_TELEGRAM_SEND_AUDIO_EXTS = {.mp3, .m4a} set.
- cron.scheduler._send_media_via_adapter now delegates the audio
decision to should_send_media_as_audio so it matches the gateway.
- Update the cron live-adapter ogg test to flag [[audio_as_voice]] so
it still routes to sendVoice under the new Telegram-specific policy.
- Tests: unit coverage for should_send_media_as_audio across platforms,
end-to-end MEDIA routing via _process_message_background and
GatewayRunner._deliver_media_from_response, TelegramAdapter.send_voice
fallback for FLAC/WAV.
Co-authored-by: Versun <me+github7604@versun.org>
Fixes the xdist collision that broke CI on PR #17764, and structurally
prevents future plugin-adapter tests from reintroducing it.
Problem
-------
tests/gateway/test_teams.py (new in this PR) and tests/gateway/test_irc_adapter.py
(already on main) both followed the same anti-pattern:
sys.path.insert(0, str(_REPO_ROOT / 'plugins' / 'platforms' / '<name>'))
from adapter import <Adapter>
Every platform plugin ships its own adapter.py, so the bare
'from adapter import ...' races for sys.modules['adapter']. Whichever test
collected first in a given xdist worker won; the other crashed at
collection with ImportError, and the polluted sys.path cascaded into 19
unrelated test failures across tools/, hermes_cli/, and run_agent/ in the
same worker.
Fix
---
1. tests/gateway/_plugin_adapter_loader.py (new): shared helper
load_plugin_adapter('<name>') that imports plugins/platforms/<name>/adapter.py
via importlib.util under the unique module name plugin_adapter_<name>.
Zero sys.path mutation, no possibility of collision.
2. tests/gateway/test_irc_adapter.py and tests/gateway/test_teams.py:
migrated to the helper. All 'from adapter import ...' statements
(including the ones inside test methods) are replaced with module-level
attribute access on the loaded module.
3. tests/gateway/conftest.py: new pytest_configure guard that AST-scans
every test_*.py under tests/gateway/ at session start and fails the
run with a pointer to the helper if any test uses sys.path.insert into
plugins/platforms/ OR a bare 'import adapter' / 'from adapter import'.
Runs on the xdist controller only (skipped in workers). The next plugin
adapter test that tries to reintroduce this pattern gets rejected at
collection time with a clear remediation message.
4. scripts/release.py: add aamirjawaid@microsoft.com -> heyitsaamir to
AUTHOR_MAP so the check-attribution workflow passes.
Validation
----------
scripts/run_tests.sh tests/gateway/ 4194 passed
scripts/run_tests.sh tests/gateway/test_{teams,irc}* 72 passed (both orderings)
scripts/run_tests.sh <11 prev-failing test files> 398 passed
Guard triggers correctly on both Path-operator and string-literal forms
of the anti-pattern.
Hello! I am the maintainer of the microsoft-teams-apps Python SDK and
I built this Teams adapter to integrate Microsoft Teams into Hermes.
Adds a `plugins/platforms/teams` platform plugin using the new
PlatformRegistry system from #17751. The adapter self-registers via
`register(ctx)` — no hardcoding in run.py, toolsets.py, or any
other core file.
Key features:
- Supports personal DMs, group chats, and channel posts
- Adaptive Card approval prompts with in-place button replacement
(Allow Once / Allow Session / Always Allow / Deny)
- aiohttp webhook server bridged from the Teams SDK to avoid
the fastapi/uvicorn dependency
- ConversationReference caching for correct proactive sends in
non-DM chats
- `interactive_setup()` for `hermes gateway setup` integration
- `platform_hint` for LLM context (Teams markdown subset)
- 34 tests covering adapter init, send, message handling, and
plugin registration
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
PR #17660 landed a sweep of CI fixes but left three loose ends:
1. tests/cli/test_cli_loading_indicator.py::test_reload_mcp_sets_busy_state_
and_prints_status — /reload-mcp gained a prompt-cache-invalidation
confirmation (commit 4d7fc0f37) that was never wired into this test.
The test exercises the loading-indicator path, so pre-approve via
config and go straight into _reload_mcp().
2. tools/mcp_tool.py _make_tool_handler — the added
getattr(server, '_rpc_lock', None) + 'skip the lock if missing'
branch is inconsistent with four sibling call sites that still
direct-access server._rpc_lock. The lock is guaranteed by
MCPServerTask.__init__; falling through to an unlocked
session.call_tool would silently serialize-strip RPCs if the guard
ever triggered. Restore direct access.
3. tui_gateway/server.py _messages_as_conversation — the helper
existed only to catch 'TypeError: include_ancestors unexpected'
from mocked SessionDBs that don't actually exist. The real
SessionDB.get_messages_as_conversation has accepted
include_ancestors since introduction, and every test FakeDB in
the repo already declares the kwarg. Remove the shim, inline the
two call sites.
* feat(plugins): bundle hermes-achievements, scan full session history
Ships @PCinkusz's hermes-achievements dashboard plugin (https://github.com/PCinkusz/hermes-achievements) as a bundled plugin at plugins/hermes-achievements/ and fixes a bug in the scan path that made the plugin only see the first 200 sessions — making lifetime badges (50k tool calls, 75k errors, etc.) unreachable on long-running installs.
Changes:
- plugins/hermes-achievements/: vendor v0.3.1 verbatim (manifest, dist/, plugin_api.py, tests, docs, README).
- plugins/hermes-achievements/dashboard/plugin_api.py:
* scan_sessions(): limit=None now scans ALL sessions via SQLite LIMIT -1. Previously capped at 200, so users with 8000+ sessions saw ~2% of their history.
* evaluate_all(): first-ever scans run in a background thread so the dashboard request path never blocks. Stale snapshots serve immediately while a background refresh runs. force=True still blocks synchronously for manual /rescan.
* _build_pending_snapshot(), _start_background_scan(), _run_scan_and_update_cache(): supporting plumbing + idempotent thread spawn.
- tests/plugins/test_achievements_plugin.py: new tests covering the 200-cap regression, the background-scan first-run flow, stale-serve-plus-background-refresh, forced sync rescan, and scan-thread idempotency.
- website/docs/user-guide/features/built-in-plugins.md: lists hermes-achievements in the bundled-plugins table and documents API endpoints, state files, and performance characteristics.
E2E validated against a real 8564-session ~6.4GB state.db:
* Cold scan: 13m 19s (one-time, backgrounded — UI never blocks)
* Warm rescan: 1.47s (8563/8564 sessions reused from checkpoint cache)
* 57/60 achievements unlocked, 3 discovered — aggregates like total_tool_calls=259958, total_errors=164213, skill_events=368243 correctly surface lifetime badges that the 200-cap made unreachable.
Original credit: @PCinkusz (MIT-licensed). Upstream repo remains the staging ground for new badges; this bundle keeps the dashboard feature parity with Hermes core changes.
* feat(achievements): publish partial snapshots during cold scan
Previously a cold scan on a large session DB (13min on 8564 sessions)
showed zero badges for the entire duration, then every badge at once
when the scan completed. A dashboard refresh mid-scan was indistinguishable
from a fresh install with no history.
Now the scanner publishes a partial snapshot to _SNAPSHOT_CACHE every
250 sessions, so each refresh during a cold scan surfaces more badges
incrementally.
Mechanism:
- scan_sessions() takes an optional progress_callback fired every
progress_every sessions with (sessions_so_far, scanned, total).
- _compute_from_scan() is extracted from compute_all() and gains an
is_partial flag that skips writing to state.json — we don't want
to record unlocked_at based on a half-complete aggregate that a
later session might rebalance.
- _run_scan_and_update_cache() installs a publisher callback that
builds a partial snapshot, marks it mode='in_progress', and writes
it to the cache with age=0 so the UI keeps polling /scan-status
and picks up the final snapshot when the scan completes.
- Manual /rescan (force=True) disables partial publishing — the
caller is blocking on the final result anyway.
E2E against real 8564-session state.db (polled cache every 10s):
t=10s: cache empty
t=20s: 250/8564 scanned, 35 unlocked, 25 discovered
t=40s: 500/8564 scanned, 42 unlocked, 18 discovered
t=60s: 1000/8564 scanned, 49 unlocked, 11 discovered
...
Tests: 9/9 pass (2 new — partial snapshot publication + no-persist-on-partial).
Upstream unittest suite: 10/10 pass.
* feat(achievements): in-progress scan banner with live % progress
Previously the dashboard showed zero badges silently during long cold
scans (13min on 8564 sessions). The backend was publishing partial
snapshots every 250 sessions, but the bundled UI didn't surface any
indicator that a scan was running — it just rendered the main page
with whatever counts were currently published and no way for the user
to know more progress was coming.
UI changes (dist/index.js, dist/style.css):
- Added a scan-in-progress banner rendered between the hero and stats
when scan_meta.mode is 'pending' or 'in_progress'. Shows:
BUILDING ACHIEVEMENT PROFILE…
Scanned 1,750 of 8,564 sessions · 20%. Badges unlock as more history streams in.
with a pulsing teal indicator and a filling teal/cyan progress bar.
Disappears the moment the backend flips to 'full' or 'incremental'.
- Added an auto-poller via useEffect — while scanInFlight is true the
page re-fetches /achievements every 4s WITHOUT toggling the loading
skeleton, so unlock counts tick up visibly without the user refreshing.
The effect cleans itself up when the scan finishes.
- Added refresh() (re-fetch, no loading flip) alongside the existing
load() (full reload, used by the Rescan button).
Attribution preserved:
- Added a header comment to index.js crediting @PCinkusz
(https://github.com/PCinkusz/hermes-achievements, MIT) as the
original author, noting the banner is a layered addition on top
of the original dist bundle.
- Matching header comment in style.css, flagging the new
.ha-scan-banner* rules as the local addition.
Live-verified end to end:
- Spun up `hermes dashboard --port 9229 --no-open` against a fresh
HERMES_HOME symlinked to the real 8564-session state.db.
- Opened /achievements in a browser, confirmed the banner renders with
live progress: 'Scanned 1,000 of 8,564 sessions · 11%' → updates to
'1,250 ... · 14%' → '1,750 ... · 20%' without user interaction,
matching the backend's partial publications.
- Stats row simultaneously climbed from 35 → 49 → 53 unlocked as
more history streamed in.
- Vision analysis of the rendered page confirms the banner styling
matches the rest of the dashboard (dark card bg, teal accent, same
small-caps typography, pulsing indicator reusing ha-pulse keyframes).
The _CODEX_AUX_MODEL constant had already rotated twice in 6 weeks
(gpt-5.3-codex -> gpt-5.2-codex -> now broken again at gpt-5.2-codex)
because ChatGPT-account Codex gates which models it accepts via an
undocumented, shifting allow-list that OpenAI publishes no changelog
for. Any pinned default will keep going stale. Issue #17533 reports
the current breakage: every ChatGPT-account auxiliary fallback fails
with HTTP 400 "model is not supported" and the 60s pause loop degrades
long sessions.
Rather than reset the clock with another stale pin (PR #17544 proposes
gpt-5.2-codex -> gpt-5.4), remove the hardcoded second-order Codex
fallback entirely:
- Delete `_CODEX_AUX_MODEL`.
- Drop `_try_codex` from `_get_provider_chain()` (the auto chain now
ends at api-key providers; 4 rungs instead of 5).
- Rename `_try_codex() -> _build_codex_client(model)` and require an
explicit model from the caller. No more guessing.
- `resolve_provider_client("openai-codex", model=None)` now warns and
returns (None, None) instead of silently guessing a stale model ID.
- Remove `_try_codex` from the `provider="custom"` fallback ladder
(same stale-constant trap).
- `_resolve_strict_vision_backend("openai-codex")` routes through
`resolve_provider_client` so the caller's explicit model is honored.
Codex-main users are unaffected: Step 1 of `_resolve_auto` already
uses `main_provider` + `main_model` directly and passes the user's
configured Codex model through `resolve_provider_client`, which never
touched `_CODEX_AUX_MODEL`. Per-task overrides (`auxiliary.<task>.provider/model`)
continue to work and are the supported way to route specific aux tasks
through Codex.
Users whose main provider fails with a payment/connection error and
who have ONLY ChatGPT-account Codex auth will now see the 60s pause
without a stale-model-rejection noise line in between -- same outcome,
cleaner failure.
Closes#17533. Supersedes #17544 (which resets the clock on the
same stale-constant problem).
Keep context-1m-2025-08-07 in OAuth requests by default so 1M-capable
subscriptions retain full context. When Anthropic rejects a request with
400 'long context beta is not yet available for this subscription',
disable the beta for the rest of the session, rebuild the client, and
retry once.
Addresses #17680 (thanks @JayGwod for the clean reproduction) without
forcing every OAuth user off the 1M context window.
Changes:
- agent/error_classifier.py: new FailoverReason.oauth_long_context_beta_forbidden;
pattern matches 400 + 'long context beta' + 'not yet available'. Narrow
enough that the existing 429 tier-gate pattern keeps its own reason.
- agent/anthropic_adapter.py: _common_betas_for_base_url,
build_anthropic_client, build_anthropic_kwargs gain drop_context_1m_beta
kwarg. Default=False (1M stays). OAuth OAUTH_ONLY_BETAS unchanged.
- agent/transports/anthropic.py: build_kwargs forwards the flag.
- run_agent.py: self._oauth_1m_beta_disabled flag, retry-once guard,
recovery branch next to the image-shrink path. _rebuild_anthropic_client
honors the flag. The main build_kwargs call site threads it through for
fast-mode extra_headers.
- hermes_cli/doctor.py, hermes_cli/models.py: sibling OAuth /v1/models
probes get the same reactive retry — previously they'd falsely report
the Anthropic API as unreachable for affected subscriptions.
Tests: 2190 tests/agent/ + 94 adjacent integration tests pass. New unit
tests cover the classifier pattern (including the collision guard against
the 429 tier-gate) and the drop_context_1m_beta adapter behavior (default
keeps 1M, flag strips only 1M while preserving every other beta).
Platform plugins shipped in-repo under plugins/platforms/ should be
available out of the box — users shouldn't have to add 'irc-platform'
to plugins.enabled before they can pick IRC from the gateway setup menu.
Adds a new ``kind: platform`` plugin type that mirrors the existing
``kind: backend`` auto-load semantics:
- Bundled (shipped in the hermes-agent repo): auto-load unconditionally.
- User-installed (~/.hermes/plugins/): still opt-in via plugins.enabled
so untrusted code doesn't silently run.
Changes:
* hermes_cli/plugins.py: add 'platform' to _VALID_PLUGIN_KINDS, document
the new kind in the PluginManifest docstring, extend the bundled auto-
load rule from 'backend only' to 'backend or platform'.
* plugins/platforms/irc/plugin.yaml: declare kind: platform.
* hermes_cli/gateway.py: remove the now-redundant
_load_bundled_platform_plugins_for_enumeration() helper and the
_enable_plugin_for_platform() helper. The setup menu's _all_platforms()
just calls discover_plugins() and reads the registry — bundled
platforms are already loaded at that point. Drops the 'needs_enable'
flag and the 'plugin disabled — select to enable' status string.
* hermes_cli/setup.py: relax the "gateway is configured" detector used
during OpenClaw migration. Switching to _platform_status() in an
earlier commit tightened the check to require an exact "configured"
match, dropping platforms whose status is "enabled, not paired",
"partially configured", "configured + E2EE", etc. Now any non-"not
configured" status counts — the user has already started setup there
and we shouldn't force the section to rerun.
* tests/hermes_cli/test_setup_irc.py: drop the TestIRCPluginDisabledFlow
class and test_configure_platform_enables_disabled_plugin_first — the
no-longer-existent flow they were testing.
* tests/hermes_cli/test_setup_openclaw_migration.py: patch both
setup.get_env_value and gateway.get_env_value in the 4 gateway-section
tests that reach _platform_status() through the unified setup flow;
switch WHATSAPP_ENABLED to the literal "true" in the registry-parity
test so WhatsApp's value-shape validator matches.
Verified via fresh-install smoke (empty plugins.enabled, no env vars):
IRC plugin loads, Platform('irc') resolves, _all_platforms() lists IRC
with status 'not configured'. 160 targeted tests pass.
feat(gateway): refine Platform._missing_ and platform-connected dispatch
Restricts plugin-name acceptance to bundled plugin scan + registry
(no arbitrary string -> enum-pollution), pulls per-platform connectivity
checks into a _PLATFORM_CONNECTED_CHECKERS lambda map with a clean
_is_platform_connected method, and adds tests covering the checker map,
plugin platform interface, and IRC setup wizard.
Merge the two gateway setup paths (hermes setup gateway + hermes gateway
setup) to use a single _unified_platforms() list that merges built-in
_PLATFORMS with dynamically registered plugin entries from
platform_registry.
- Add setup_fn field to PlatformEntry for plugin setup flows
- _unified_platforms() merges built-ins with registry entries by key
- setup_gateway() now uses unified list instead of hardcoded
_GATEWAY_PLATFORMS tuple list
- gateway_setup() uses same unified list, plugin entries appear
alongside built-ins with no [plugin] suffix
- _platform_status() handles plugin platforms via registry check_fn
- Plugin platforms with setup_fn get called directly; plugins without
get a generic env-var display fallback
IRC and other plugin platforms now appear automatically in the setup
menu when registered via platform_registry.register().
feat(gateway): surface disabled platform plugins in setup and auto-enable on select
Platform plugins under plugins/platforms/* (IRC, etc.) were gated behind
plugins.enabled, so `hermes gateway setup` wouldn't list them until the
user ran `hermes plugins enable <name>` first. Now the setup menu always
surfaces them as "plugin disabled — select to enable", and picking one
adds it to plugins.enabled before running its setup flow.
Along the way, unify the two gateway setup flows so `hermes setup gateway`
and `hermes gateway setup` both read from the same platform list (built-in
_PLATFORMS + platform_registry entries), dispatch through a single
_configure_platform() helper, and share _platform_status(). Deletes the
dead bespoke wrappers in setup.py (_setup_whatsapp, _setup_weixin,
_setup_email, etc.) that duplicated logic now covered by the registry
path or _setup_standard_platform.
Also:
- PlatformEntry gains a plugin_name field so the registry knows which
plugin owns each entry (required for auto-enable).
- PluginContext.register_platform auto-stamps plugin_name from the
manifest so plugins don't have to pass it explicitly.
- PluginManager now scans plugins/platforms/* as its own category root,
one level below the bundled plugin scan.
- Fix IRC plugin discovery: rename PLUGIN.yaml → plugin.yaml (the
scanner is case-sensitive) and add the missing __init__.py that
_load_directory_module requires.
Extends the platform plugin interface from Phase 1 to cover every
touchpoint where built-in platforms have hardcoded behavior.
- allowed_users_env / allow_all_env: per-platform auth env vars
- max_message_length: smart-chunking for send_message tool
- pii_safe: session PII redaction flag
- emoji: CLI/gateway display
- allow_update_command: /update access control
send_message tool (tools/send_message_tool.py):
- Replaced hardcoded platform_map dict with Platform() call
- Added _send_via_adapter() for plugin platforms — routes through
live gateway adapter when available
- Registry-aware max message length for smart chunking
Cron delivery (cron/scheduler.py):
- Replaced hardcoded 15-entry platform_map with Platform() call
- Plugin platforms now work as cron delivery targets
User authorization (gateway/run.py _is_user_authorized):
- Registry fallback: checks PlatformEntry.allowed_users_env and
allow_all_env when platform not in hardcoded maps
- Plugin platforms get per-platform auth support
_UPDATE_ALLOWED_PLATFORMS: checks registry allow_update_command flag
Channel directory: includes plugin platforms in session enumeration
Orphaned config warning: descriptive message when plugin platform is
in config but no plugin registered it
Gateway weakref: _gateway_runner_ref for cross-module adapter access
hermes status: shows plugin platforms with (plugin) tag
hermes gateway setup: plugin platforms appear in menu with setup hints
hermes_cli/platforms.py: get_all_platforms() merges with registry,
platform_label() falls back to registry for plugin names
- 8 new tests (extended fields, cron resolution, platforms merge)
- Updated 3 tests for new Platform() based resolution
- 2829 passed, 24 pre-existing failures, zero new failures
Adds a platform adapter plugin interface so anyone can create new gateway
platforms (IRC, Viber, Line, etc.) as drop-in plugins without modifying
core gateway code.
- PlatformEntry dataclass: name, label, adapter_factory, check_fn,
validate_config, required_env, install_hint, source
- PlatformRegistry singleton with register/unregister/create_adapter
- _create_adapter() in gateway/run.py checks registry first, falls
through to existing if/elif chain for built-in platforms
- Platform._missing_() accepts unknown string values, creating cached
pseudo-members so Platform('irc') is Platform('irc') holds true
- GatewayConfig.from_dict() now parses plugin platform names from
config.yaml without rejecting them
- get_connected_platforms() delegates to registry for unknown platforms
- PluginContext.register_platform() for plugin authors
- Mirrors the existing register_tool() / register_hook() pattern
- Full async IRC adapter using stdlib asyncio (zero external deps)
- Connects via TLS, handles PING/PONG, nick collision, NickServ auth
- Channel messages require addressing (nick: msg), DMs always dispatch
- Markdown stripping for IRC-clean output, message splitting for
512-byte line limit
- Config via config.yaml extra dict or IRC_* env vars
- Platform enum dynamic members (identity stability, case normalization)
- PlatformRegistry (register, unregister, create, validation, factory)
- GatewayConfig integration (from_dict parsing, get_connected_platforms)
- IRC adapter (init, send, protocol parsing, markdown, requirements)
No existing platform adapters were migrated — the if/elif chain is
untouched. This is Phase 1: prove the interface with a real plugin.
Reloading MCP servers rebuilds the tool set for the active session, which
invalidates the provider prompt cache (tool schemas are baked into the
system prompt). The next message re-sends full input tokens — can be
expensive on long-context or high-reasoning models.
To surface that cost, /reload-mcp now routes through a new slash-confirm
primitive with three options: Approve Once / Always Approve / Cancel.
'Always Approve' persists approvals.mcp_reload_confirm: false so future
reloads run silently.
Coverage:
* Classic CLI (cli.py) — interactive numbered prompt.
* TUI (tui_gateway + Ink ops.ts) — text warning on first call; `now` /
`always` args skip the gate; `always` also persists the opt-out.
* Messenger gateway — button UI on Telegram (inline keyboard), Discord
(discord.ui.View), Slack (Block Kit actions); text fallback on every
other platform via /approve /always /cancel replies intercepted in
gateway/run.py _handle_message.
* Config key: approvals.mcp_reload_confirm (default true).
* Auto-reload paths (CLI file watcher, TUI config-sync mtime poll) pass
confirm=true so they do NOT prompt.
Implementation:
* tools/slash_confirm.py — module-level pending-state store used by all
adapters and by the CLI prompt. Thread-safe register/resolve/clear.
* gateway/platforms/base.py — send_slash_confirm hook (default 'Not
supported' → text fallback).
* gateway/run.py — _request_slash_confirm helper + text intercept in
_handle_message (yields to in-progress tool-exec approvals so
dangerous-command /approve still unblocks the tool thread first).
Tests:
* tests/tools/test_slash_confirm.py — primitive lifecycle + async
resolution + double-click atomicity (16 tests).
* tests/hermes_cli/test_mcp_reload_confirm_gate.py — default-config
shape + deep-merge preserves user opt-out (5 tests).
Targeted runs (hermetic): 89 passed (slash-confirm, config gate,
existing agent cache, existing telegram approval buttons).
PR #15027 (5 days ago) shipped TELEGRAM_GROUP_ALLOWED_USERS as a chat-ID
allowlist. #17686 correctly renames that to sender user IDs and moves
chat IDs to TELEGRAM_GROUP_ALLOWED_CHATS. Without a shim, any user on
PR #15027's guidance would silently start rejecting group traffic on
upgrade.
- gateway/run.py: in _is_user_authorized, if TELEGRAM_GROUP_ALLOWED_USERS
contains values starting with '-' (chat-ID-shaped), honor them as chat
IDs and log a one-shot deprecation warning pointing users at the new
TELEGRAM_GROUP_ALLOWED_CHATS var.
- tests/gateway/test_unauthorized_dm_behavior.py: three new tests cover
legacy chat-ID values authorizing the listed chat, not crossing to
other chats, and mixed sender/chat values in the same var.
- website/docs/user-guide/messaging/telegram.md: rewrite the Group
Allowlisting section to document the new user/chat split + migration
note. Remove stale '/thread_id' suffix claim (code never parsed it).
- website/docs/reference/environment-variables.md: document all three
Telegram allowlist env vars.
Salvage-follow-up to @shannonsands's /reload-skills PR. Trims the feature to
match the design: user-initiated rescan, no prompt-cache reset, no new
schema surface, no phantom user turn, and the next-turn note carries each
added/removed skill's 60-char description (not just its name).
Changes vs the original PR:
* Drop the in-process skills prompt-cache clear in reload_skills(). Skills
are invoked at runtime via /skill-name, skills_list, or skill_view —
they don't need to live in the system prompt for the model to use them.
Keeping the cache intact preserves prefix caching across the reload so
/reload-skills pays no cache-reset cost. (MCP has to break the cache
because tool schemas must be known at conversation start; skills do not.)
* Drop the skills_reload agent tool and SKILLS_RELOAD_SCHEMA from
tools/skills_tool.py, plus the four skills_reload enumerations in
toolsets.py. No new schema surface — agents can already see a freshly-
installed skill via skill_view / skills_list the moment it's on disk.
* Replace the phantom 'role: user' turn injection with a one-shot queued
note. CLI uses self._pending_skills_reload_note (same pattern as
_pending_model_switch_note, prepended to the next API call and cleared).
Gateway uses self._pending_skills_reload_notes[session_key]. The note
is prepended to the NEXT real user message in this session, so message
alternation stays intact and nothing out-of-band is persisted to the
transcript.
* reload_skills() now returns added/removed as
[{'name': str, 'description': str}, ...] (description truncated to 60
chars — matches the curator / gateway adapter budget). The injected
next-turn note formats each entry as 'name — description' so the model
can actually reason about which new skills to call without running
skills_list first.
* Only emit the note when the diff is non-empty. On empty diff, print
'No new skills detected' and do nothing else.
* Tests rewritten to cover the queue semantics, the description payload,
and a regression guard that the prompt-cache snapshot is preserved.
Adds a public reload path for the in-process skill caches so newly
installed (or removed) skills become visible mid-session without a
gateway restart. Mirrors the shape of /reload-mcp.
Three surfaces:
* /reload-skills slash command — CLI (cli.py) and gateway (gateway/run.py),
with /reload_skills alias for Telegram autocomplete and an explicit
Discord registration.
* skills_reload agent tool (tools/skills_tool.py) — lets agents/subagents
pick up freshly-installed skills via tool call.
* agent.skill_commands.reload_skills() — shared helper that clears
_skill_commands, _SKILLS_PROMPT_CACHE (in-process LRU), and the
on-disk .skills_prompt_snapshot.json, then returns an added/removed
diff plus the new total count.
Tested:
* tests/agent/test_skill_commands_reload.py (9 cases)
* tests/cli/test_cli_reload_skills.py (3 cases)
* tests/gateway/test_reload_skills_command.py (4 cases)
Use case: NemoClaw / OpenShell-style sandboxed orchestrators that drop
skills into ~/.hermes/skills mid-session, plus agentic flows where the
agent itself installs a skill via the shell tool and needs it bound
without a gateway restart. The Python helper
clear_skills_system_prompt_cache(clear_snapshot=True) already exists
internally — this PR just exposes it via slash command and tool.
Pull the top-level + chat parser construction out of main() into
hermes_cli/_parser.py so relaunch.py can introspect parser._actions to
discover which flags exist and whether they take values, instead of
maintaining a parallel hand-rolled (flag, takes_value) tuple list.
- _parser.py: build_top_level_parser() returns (parser, subparsers,
chat_parser); side-effect-free import.
- main.py: ~290 lines of inline parser construction collapsed to a
helper call. Other subparsers stay inline (dispatch is bound to
module-level cmd_* functions).
- _parser._inherited_flag(parser, ...): wraps parser.add_argument and
sets action.inherit_on_relaunch = True. Used in place of
parser.add_argument for the 25 flags (top-level + chat) that need to
carry over.
- _parser.PRE_ARGPARSE_INHERITED_FLAGS: holds --profile/-p, which
isn't on argparse (consumed earlier by main._apply_profile_override).
- relaunch.py: drops _CRITICAL_DESTS and _PRE_ARGPARSE_FLAGS; the table
builder now filters by getattr(action, 'inherit_on_relaunch', False).
- test_ignore_user_config_flags.py: brittle inspect.getsource grep
replaced with proper parser introspection.
- test_relaunch.py: introspection sanity tests added.
Salvaged from PR #17549; added top-level -t/--toolsets flag to
_parser.py so #17623 (fix(tui): honor launch toolsets) behavior is
preserved on current main.
Co-authored-by: ethernet <arilotter@gmail.com>
Extract all os.execvp('hermes', ...) calls into a utility so flags like
--tui, --dev, --profile, --model, --provider, et al. survive session
resume and post-setup relaunch.
- resolve_hermes_bin: prefers sys.argv[0] when callable, then PATH,
then falls back to '${sys.executable} -m hermes_cli.main' (fixes nix
run relaunches)
- build_relaunch_argv: allowlists critical flags so they carry over
- cmd_sessions browse now calls relaunch(['--resume', <id>])
- _apply_profile_override skips redundant work when HERMES_HOME is
already set (child inherits parent profile)
- setup.py replaces _resolve_hermes_chat_argv with relaunch_chat()
- added comprehensive tests for flag extraction and binary resolution
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
If a concurrent RPC mutates _sessions while session.delete is iterating
it (e.g. a parallel session.create on the thread pool), the bare except
swallowed the RuntimeError and let the delete proceed against a row
that may still be live. Snapshot via list(_sessions.values()) and
return an error when even that raises, instead of treating "couldn't
check" as "no active sessions."
Pressing `d` on the highlighted row in the resume picker prompts
`delete? y/n`; `y` deletes the session (DB row + on-disk transcript
files), anything else cancels. The active session is excluded from
deletion server-side.
Adds a new `session.delete` JSON-RPC handler that wraps
`SessionDB.delete_session`, forwarding the per-profile `sessions/`
directory so transcripts get cleaned up alongside the row.
CI Tests workflow has been red on main for 40+ consecutive runs. This
commit recovers every failure visible in run 25130722163 (most recent
completed run prior to this PR).
Root causes, by group:
Test-mock drift after product landed (fix: update mocks)
- test_mcp_structured_content / test_mcp_dynamic_discovery (6 tests):
product added _rpc_lock (#02ae15222) and _schedule_tools_refresh
(#1350d12b0) without updating sibling test files. Install a real
asyncio.Lock inside the fake run-loop and patch at _schedule_tools_refresh.
- test_session.py: renamed normalize_whatsapp_identifier → canonical_
whatsapp_identifier upstream; keep a local alias so the legacy tests
keep working.
- test_run_progress_topics Slack DM test: PR #8006 made Slack default
tool_progress=off; explicitly set it to 'all' in the test fixture so
the progress-callback path still runs. Also read tool_progress_callback
at call time rather than freezing it in FakeAgent.__init__ — production
assigns it AFTER construction.
- test_tui_gateway_server session-create/close race: session.create now
defers _start_agent_build behind a 50ms timer — wait for the build
thread to enter _make_agent before closing, otherwise the orphan-
cleanup path never runs.
- test_protocol session.resume: product get_messages_as_conversation now
takes include_ancestors kwarg; accept **_kwargs in the test stub.
- test_copilot_acp_client redaction: redactor is OFF by default (snapshots
HERMES_REDACT_SECRETS at import); patch agent.redact._REDACT_ENABLED=True
for the duration of the test.
- test_minimax_provider: after #17171, dots in non-Anthropic model names
stay dots even with preserve_dots=False. Assert the new invariant
rather than the old 'broken for MiniMax' behavior.
- test_update_autostash: updater now scans `ps -A` for dashboard PIDs;
the test's catch-all subprocess.run stub needed stdout/stderr fields.
- test_accretion_caps: read_timestamps dict is populated lazily when
os.path.getmtime succeeds. Use .get("read_timestamps", {}) to tolerate
CI filesystems where the stat races file creation.
Change-detector tests (fix: rewrite as structural invariants)
- test_credential_sources_registry_has_expected_steps: was a frozen set
comparison that broke when minimax-oauth was added. Rewrite as an
invariant check (every step has description, no dupes, core steps
present) per AGENTS.md 'don't write change-detector tests'.
xdist ordering / test pollution (fix: reset state, use module-local patches)
- test_setup vercel: sibling test saved VERCEL_PROJECT_ID='project' to
os.environ via save_env_value() and never cleared it. monkeypatch.delenv
the VERCEL_* vars in the link-file test.
- test_clipboard TestIsWsl: GitHub Actions is on Azure VMs whose real
/proc/version often contains 'microsoft'. Patching builtins.open with
mock_open didn't reliably intercept hermes_constants.is_wsl's call in
xdist workers that had already cached _wsl_detected=True from an
earlier test. Patch hermes_constants.open directly and add
teardown_method to reset the cache after each test.
Pytest-asyncio cancellation hangs (fix: bound product await with timeout)
- test_session_split_brain_11016 (3 params) + test_gateway_shutdown
cancel-inflight: under pytest-asyncio 1.3.0, 'await task' and
'asyncio.gather(cancelled_tasks)' can stall for 30s when the cancelled
task's finally block awaits typing-task cleanup. Bound both with
asyncio.wait_for(..., timeout=5.0) and asyncio.shield — the stragglers
are released from adapter tracking and allowed to finish unwinding in
the background. This is also a legitimate hardening: a wedged finally
shouldn't stall the caller's dispatch or a gateway shutdown.
Orphan UI config (fix: merge tiny tab into messaging category)
- test_web_server test_no_single_field_categories: the telegram.reactions
config field lived in its own 'telegram' schema category with no
siblings. Fold it under 'discord' via _CATEGORY_MERGE so the dashboard
doesn't render an orphan single-field tab.
Local verification: 38/38 originally-failing tests pass; 4044/4044
gateway tests pass; 684/684 targeted subset (all 16 touched test files)
passes.
Detect leaked SGR mouse-report fragments in CLI input, strip them, and reset terminal modes in-place so scroll and typing recover without reopening the tab. Add regression tests for escaped, visible, and bare leak forms.
