Commit Graph

2801 Commits

Author SHA1 Message Date
Teknium 89f920901b feat(mcp): warn on hidden whitespace in MCP config values
Inspired by Claude Code v2.1.219: MCP config string values with hidden
leading/trailing whitespace (pasted tokens with trailing newlines, URLs
with leading spaces) now trigger a startup warning naming the server and
the dotted key path, instead of failing later as an opaque auth/connect
error.

Advisory only: values are never mutated, secrets are never logged (only
key paths), and warnings dedupe to once per process per (server, path).
Checked after ${VAR} interpolation so whitespace inside referenced env
vars is caught too.
2026-07-31 21:21:10 -07:00
Austin Pickett e444d16580
fix(vision): make desktop image uploads reachable from profile Docker sandboxes (#69575) (#75671)
* fix(vision): mount images/ upload dir into sandboxes and permit host read (#69575)

Desktop, clipboard, and PDF uploads land in the flat top-level
HERMES_HOME/images/ dir, but Docker sandboxes only mounted the cache/
subtree and the vision resolver only permitted host reads from the media
caches. So vision_analyze on any desktop-app upload failed under a Docker
backend with "not reachable inside the sandbox".

- Add ("images", "images") to _CACHE_DIRS so the uploads dir is bind-mounted
  into sandbox containers through the existing profile-scoped cache-mount and
  reverse-mapping mechanism.
- Add home/"images" to _media_cache_roots() so the non-local host-read
  allowlist permits reading uploads directly from the host filesystem.
- Cover the mount entry, the container path mapping, and the Docker-mode
  resolver read for a profile-scoped upload.

Co-authored-by: JonthanaHanh <92574114+JonthanaHanh@users.noreply.github.com>
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>

* fix(tui_gateway): write image uploads under the session's profile home (#69575)

The attach RPCs (image.attach_bytes, clipboard.paste, pdf.attach) wrote
uploads to the gateway's module-cached launch home via _hermes_home/"images".
Those RPCs run before prompt.submit installs the session's profile HERMES_HOME
override, so in a multi-profile / root-gateway deployment the file landed in
the launch home while the sandbox mount and the vision host-read allowlist
both resolve the session profile's images/ at run time — the agent could
never see the upload it was handed.

Add _session_images_dir(session), which anchors the write on the session's
stored profile_home when present (matching the mount/read scope) and falls
back to the launch home otherwise. Route both write sites through it, keeping
per-profile isolation.

Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>

---------

Co-authored-by: JonthanaHanh <92574114+JonthanaHanh@users.noreply.github.com>
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>
2026-07-31 17:43:37 -04:00
Brooklyn Nicholson e41d2029b7 fix(sessions): keep kanban worker runs out of the session lists
Exclude the source from the desktop sidebar and project tree, the TUI
resume picker, session_search, and the CLI session listings.
2026-07-31 13:53:04 -05:00
ethernet 6ecd335aa8
Merge pull request #75037 from NousResearch/sec-fixes
fix(sec): patch vulnerable deps + add publication-age floors and npm script allow-list

Co-authored-by: Kingsley Wong <7207924+datanerdie@users.noreply.github.com>
Co-authored-by: viky <vikyw89@gmail.com>
Co-authored-by: FT_IOxCS <237263164+ft-ioxcs@users.noreply.github.com>
Co-authored-by: 方明元 <fmy3@qq.com>
Co-authored-by: Yorkstone Supplies <58149681+sycamoregroupltd@users.noreply.github.com>
Co-authored-by: Steven Cuz Leath <Steven.Leath@gmail.com>
Co-authored-by: Kyle French <248366920+Dadmin88@users.noreply.github.com>
Co-authored-by: Eugeniusz Gilewski <egilewski@egilewski.com>
Co-authored-by: Christopher Gara <79837758+christopherrobin88@users.noreply.github.com>
Co-authored-by: LironTTG <147833337+LironTTG@users.noreply.github.com>
Co-authored-by: Austin Porada <bbasketballer75@gmail.com>
Co-authored-by: cresslank <9219265+cresslank@users.noreply.github.com>
Co-authored-by: Ion Mudreac <mudreac@gmail.com>
Co-authored-by: martinramos002 <262243228+martinramos002-bot@users.noreply.github.com>
Co-authored-by: Sensie-Agents <agents@joinsensie.com>
Co-authored-by: alexwill87 <173086651+alexwill87@users.noreply.github.com>
Co-authored-by: BullishMomentum56 <218643122+BullishMomentum56@users.noreply.github.com>
Co-authored-by: pintadoai <240097310+pintadoai@users.noreply.github.com>
Co-authored-by: Alfred Sahlberg <dinmail@gmail.com>
Co-authored-by: liuhao1024 <sunsky.lau@gmail.com>
Co-authored-by: Richard Ham <richard.ham@live.com>
Co-authored-by: jrcrittenden <jrcrittenden@gmail.com>
Co-authored-by: 峯岸 亮 <1920071390@campus.ouj.ac.jp>
Co-authored-by: Marcus Martini <6473852+napoleonmm83@users.noreply.github.com>
2026-07-31 14:07:32 -04:00
brooklyn! 0324849fe4
Merge pull request #61173 from NousResearch/bb/desktop-kanban
feat(desktop): Kanban — the founding plugin on the desktop SDK
2026-07-31 13:00:10 -05:00
ethernet abcd213504 fix(sec): update pillow to 12.3.0
pillow 12.2.0 has 26 known vulnerabilities:

GHSA-45hq-cxwh-f6vc
GHSA-4x4j-2g7c-83w6
GHSA-5x94-69rx-g8h2
GHSA-62p4-gmf7-7g93
GHSA-6r8x-57c9-28j4
GHSA-8v84-f9pq-wr9x
GHSA-9hw9-ch79-4vh6
GHSA-fj7v-r99m-22gq
GHSA-jjj6-mw9f-p565
GHSA-pg7v-jwj7-p798
GHSA-phj9-mv4w-65pm
GHSA-vjc4-5qp5-m44j
GHSA-xj96-63gp-2gmr
PYSEC-2026-2253
PYSEC-2026-2254
PYSEC-2026-2255
PYSEC-2026-2256
PYSEC-2026-2257
PYSEC-2026-3451
PYSEC-2026-3452
PYSEC-2026-3453
PYSEC-2026-3454
PYSEC-2026-3493
PYSEC-2026-3494
PYSEC-2026-3495
PYSEC-2026-3496

they're fixed in >= 12.3.0
2026-07-31 13:42:03 -04:00
ethernet a7efeb0829 fix(sec): update mcp to 1.28.1
mcp 1.26.0 has 3 known vulnerabilities: PYSEC-2026-3481,
PYSEC-2026-3482, PYSEC-2026-3483

they're fixed in >= 1.28.1
2026-07-31 13:42:03 -04:00
Alex Fournier e3d10f0a8f Merge current tool metrics into skill metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-31 07:54:38 -07:00
Alex Fournier 1318c213b0 Merge current model route metrics into tool metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-31 07:54:13 -07:00
Alex Fournier 3d5fcab70f Merge updated tool metrics into skill metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>

# Conflicts:
#	hermes_cli/observability/schemas/hermes.shared_metrics.v1.schema.json
#	scripts/smoke_nemo_relay_shared_metrics.py
#	tests/agent/test_skill_commands.py
#	tests/hermes_cli/test_relay_shared_metrics.py
#	tests/hermes_cli/test_relay_shared_metrics_runtime.py
#	tests/tools/test_skill_manager_tool.py
#	tests/tools/test_skill_usage.py
#	tests/tools/test_skills_tool.py
2026-07-31 07:30:30 -07:00
Alex Fournier aef76ba398 Merge updated model metrics into tool metrics
# Conflicts:
#	hermes_cli/observability/shared_metrics_contract.py
#	hermes_cli/observability/shared_metrics_subscriber.py
#	scripts/smoke_nemo_relay_shared_metrics.py
#	tests/hermes_cli/test_plugins.py
#	tests/hermes_cli/test_relay_shared_metrics.py
#	tests/hermes_cli/test_relay_shared_metrics_runtime.py
#	tests/run_agent/test_run_agent.py
#	tests/test_model_tools.py
#	tests/tools/test_approval.py
2026-07-31 07:18:02 -07:00
rob-maron 126ff7071b
Portal free user vision fix + flux3 polling improvements (#75448)
* flux3 polling improvments

* poll gap to 4s

* back to 5s

* vision model fix

* minor fix
2026-07-31 10:17:55 -04:00
kshitijk4poor 98105f31f4 fix(file_ops): harden new-file umask chmod for portability
Follow-ups on top of #70888's cherry-picked fix:

- Replace the $((0666 & ~0$u)) shell arithmetic with POSIX who-less
  'chmod "=rw"'. zsh (reachable via _find_bash's $SHELL fallback on
  bash-less hosts) parses leading-zero constants as decimal and silently
  chmods a garbage mode (e.g. 0210); the symbolic form is spec-identical
  across bash/dash/busybox-ash/zsh and degrades to mktemp's 0600
  (pre-fix behavior) rather than corrupting perms if chmod rejects it.
- Move the new-file chmod after the content stream so the temp file
  stays owner-writable while cat runs.
- Run the chmod on a '[ ! -e "$t" ]' check after cat instead of the
  stat/else branch, keeping the overwrite path untouched.
- Update the stale perms comment #70856 called out (new files did NOT
  land with default umask perms pre-fix).
- Tests: select the atomic-write script by content instead of call
  order (the previous last-call capture only worked because the bare
  MagicMock's falsy-exit early return suppressed later execs), assert
  behavior at explicit umasks 0022/0002/0077 via parametrize, add an
  overwrite mode-preservation regression guard, and dedupe the
  real-subprocess env fake into make_real_subprocess_env() shared with
  TestSearchFilesFallbackHiddenPaths.

(webtecnica's email mapping already exists in contributors/emails/ on
current main; the PR's check-attribution red was stale-base only.)

# Conflicts:
#	tests/tools/test_file_operations.py
2026-07-31 14:22:38 +05:30
Ben Barclay ce6dd1a65f
fix(sync): read org state from the org endpoints, not the personal ones (#75237)
Org-shared skills were unusable past the first propose. Three defects, one
root cause plus two that it masked.

ROOT CAUSE — org reads went to the personal endpoint.

`SyncClient.get_refs()` / `get_object()` only ever called `/v1/sync/refs`
and `/v1/sync/objects/:hash`. Those routes are hard-scoped server-side to
the token's own owner, so asking them for `refs/org/<id>/` returns the
caller's PERSONAL refs rather than an error, and org objects 404. Both org
call sites read org state through them:

- `pull_org_skills` resolved head=None for a populated org and reported
  `{"ok": true, "head": null, "updated": []}` — org skills silently never
  arrived, which reads as "my org has no skills" rather than as a failure.
- `propose_skill` resolved base_head=None, so the FIRST propose to an org
  succeeded by accident (`from: null` happened to be correct) and EVERY
  later one CAS'd against a head it had never seen -> 409 -> a raw
  `SyncConflict` traceback. Worse, it built its root from an empty skill
  map, so a landed CAS would have REPLACED the org set rather than splicing
  into it — the 409 was accidentally preventing data loss.

Fix: `org_scope=True` on `get_refs`/`get_object`, threaded through
`get_commit_json`, `get_tree_json`, `_root_tree_of_commit`,
`_skill_trees_of_root`, and `materialize_tree` — walking an org commit needs
the org route on every hop, not just the first. Both org call sites now go
through one `_read_org_head()` helper.

ALSO FIXED

- `propose_skill` retries on conflict. When the org HEAD moves between the
  read and the CAS (another member proposing, an admin merging), it
  re-splices this one skill onto the NEW head and retries, bounded at 5
  attempts. Re-splicing rather than replaying the old root is what stops a
  concurrent proposal being dropped.
- An empty `actual` in a 409 means "the ref does not exist", not "here is a
  commit". `SyncConflict` normalizes "" to None in its constructor, and the
  personal push path redoes the CAS as a create instead of fetching "" as an
  object — which surfaced as the baffling `object  not found` (doubled
  space). This is what a client hits after switching sync planes, since
  `.sync_state` is not environment-scoped and carries a foreign head.

THE MOCK WAS THE REASON THIS SHIPPED

The test mock served org refs and org objects off the personal routes, so
21 org tests passed against a client that could not work against the real
plane. The mock now mirrors production: `/v1/sync/org/refs` and
`/v1/sync/org/objects/:hash` exist, org objects live in a separate scope,
and the personal routes refuse org content. Two existing tests had to be
corrected to assert against the org scope — they had been passing on the
mock's over-permissiveness.

Tests: 5 new (org head invisible on the personal route; second propose
splices and preserves the first; pull resolves a real org head; empty
`actual` -> None; push recovers from a stale cross-plane head). Verified
they FAIL without the fix: reverting just `_read_org_head` to the personal
route fails the second-propose test and the pre-existing splice test.
1278 passed / 0 failed across 54 suites via scripts/run_tests.sh.

Verified against PRODUCTION with a real org token, not just the mock:
- `pull_org_skills` -> head `sha256:1adf9333…`, materialized
  `software-development/gateway-gateway-connector` into the `_org` mirror
  (was head=None, updated=[]).
- A second `hermes sync propose` succeeded where it previously raised, and
  the org set afterwards contains BOTH skills with the new commit
  descending from the first.
2026-07-30 22:31:42 -07:00
rob-maron 4c7cc62f9f flux3 messaging system fixes 2026-07-30 15:20:09 -07:00
rob-maron 4a798f4bce
improve polling for FLUX3 video gen (#75010)
* wait between polls
2026-07-30 16:29:27 -04:00
rob-maron 07447bd5db
nous portal video gen (#74963) 2026-07-30 14:52:15 -04:00
webtecnica fbfee8e405 fix(file_ops): apply umask-default permissions in _atomic_write for new files (#70856) 2026-07-30 21:53:38 +05:30
Brooklyn Nicholson 901205420f feat(kanban): talk to a running worker without a restart
A running worker now polls its comment thread and folds new operator notes
into the live turn via the OUT-OF-BAND steer channel (list_comments_after +
a heartbeat-driven bridge, watermarked so history isn't re-injected and the
worker's own notes are skipped). No block→comment→unblock dance. Desktop's
composer sends notes live ("delivered within a few seconds") with "Requeue
with note" as the restart option and a help tooltip.
2026-07-30 07:18:08 -05:00
Brooklyn Nicholson fec1ac0a7a feat(desktop): reactions are opt-in under Settings → Appearance, off by default
One lever, every surface. The renderer toggle persists locally and mirrors
into display.message_reactions; the backend gates the agent's
react_to_message tool (check_fn) and the model-context annotation on the same
key, and the ':' composer trigger reads the store at detection time. Off
means off everywhere: no ☺ slot, no right-click picker, no :shortcode:
popover, no agent reactions, and the model hears nothing — while reactions
already persisted keep rendering so history doesn't lose data. Also fixes the
import-order lint error CI flagged in composer/index.tsx.
2026-07-30 00:08:28 -05:00
Brooklyn Nicholson 7d92056c49 feat(gateway): iMessage-style message reactions — storage, RPC, agent tool, model context
Reactions live in the existing messages.display_metadata JSON column (no new
table), with iOS Tapback semantics enforced DB-side: one reaction per author
per message, re-tap retracts, different emoji replaces. The desktop catches up
to the reaction contract five platform adapters already ship.

- SessionDB: set/get_message_reaction, latest_message_row_id (role + offset +
  require_text so invisible tool-call-only rows are never targeted),
  take_unseen_reactions (announce-exactly-once), get_message_role
- message.react RPC: accepts row_id or newest_role for live messages that
  haven't learned their durable id yet
- react_to_message tool: desktop-gated (check_fn), defaults to the user's
  latest visible message, messages_back for retroactive reactions
- Model context rides run_message only (beside the speech-interrupted note):
  the persisted prompt stays clean, so no [The user reacted …] scaffolding in
  transcripts, and no cached prefix ever changes
- Resume projection forwards row_id + reactions; _row_id is stripped from
  outgoing API copies next to display_metadata
2026-07-30 00:08:28 -05:00
Teknium c770515e2b modernize re-added Vercel integrations: SDK 0.7.2, telemetry off, sibling-site wiring
- Bump vercel SDK pin 0.5.7 -> 0.7.2 (pyproject, lazy_deps) and regenerate uv.lock
- Disable the SDK's new default-on telemetry (VERCEL_TELEMETRY_DISABLED=1
  set before import, user-overridable) per the no-opt-out-telemetry policy
- Move _model_flow_ai_gateway into hermes_cli/model_setup_flows.py (god-file
  decomposition landed after the removal)
- Widen post-removal backend sets that vercel_sandbox missed: terminal_tool
  container_backend + _CONTAINER_BACKENDS, file_tools fallback set,
  env_probe._REMOTE_BACKENDS, approval._should_skip_container_guards,
  prompt_builder probe container_config
- Add terminal.vercel_runtime to config_defaults + TERMINAL_CONFIG_ENV_MAP
- Re-add vercel dependency group to nix #full variant (reverts #33773 workaround)
- Update restored tests to current contracts: upload-only credential sync-back
  (bcfc7458fa), registry-derived provider env list, parametrized backend fixture,
  drop tests superseded on main (slack wizard move #41112, nous status format)
2026-07-29 19:48:37 -07:00
Teknium ad12df6ba4 Revert "remove Vercel AI Gateway and Vercel Sandbox (#33067)"
This reverts commit febc4cfec0.
2026-07-29 19:48:37 -07:00
Jorkey Liu 05afea65f4 fix(session): resolve default state DB path at call time
DEFAULT_DB_PATH in hermes_state.py is computed at import time, freezing
the developer's real ~/.hermes even when a test fixture (or runtime
profile switch) later redirects HERMES_HOME. Any default SessionDB() —
e.g. gateway SessionStore — then opened the real state.db.

Add _default_db_path(): resolves get_hermes_home() fresh at call time,
while a deliberately re-pointed DEFAULT_DB_PATH (the established
monkeypatch escape hatch) still wins via an import-time snapshot
comparison, preserving existing test behavior. SessionDB.__init__ and
session_search's requirement check now use the resolver; explicit
db_path arguments are untouched.

Reimplemented from PR #11875 by @JorkeyLiu (original diff predates the
hermes_state rewrite); regression test ported and modernized.
2026-07-29 18:55:10 -07:00
Jasmine Naderi 92914e9b09 fix(state): restore async_delegation.py symbols, keep only journal_mode routing
The previous commit accidentally reverted async_delegation.py to a
pre-origin_session_id snapshot, dropping _MAX_DELIVERY_ATTEMPTS,
_current_origin_session_id, _transaction(), the origin_session_id
column, and drop_completion_delivery() — causing ImportError in
delegate_tool.py and kanban_tools.py.

This restores the upstream main version of async_delegation.py and
re-applies only the journal_mode routing change (db_label update to
'async_delegation.db').

Addresses reviewer feedback on #68912.

Signed-off-by: Jasmine Naderi <jasmine@smfworks.com>
2026-07-29 18:13:09 -07:00
Jasmine Naderi 04ec841462 fix(state): configurable journal_mode + centralize all DB openers
Add HERMES_JOURNAL_MODE env / database.journal_mode config for
virtiofs/NFS/SMB where WAL is not crash-safe. Route 5 bypass openers
through apply_wal_with_fallback so a single setting covers every .db
(#68545).
2026-07-29 18:13:09 -07:00
Teknium 1a088989bc
Merge pull request #66730 from NousResearch/feat/hsp-sync-client
feat(sync): HSP/1 personal skill sync client (M1 client)
2026-07-29 15:20:35 -07:00
kshitijk4poor 1f70ba6bca fix(mcp): propagate cancellation untouched in _connect_server orphan reap
Follow-up to the salvaged #62026 ownership fix, folding in #72054's
CancelledError rule by @adurham: start() already cancels/reaps its own
run task when the caller's connect timeout cancels start() itself, so
_connect_server() must propagate cancellation without awaiting a
redundant shutdown() inside a cancelled context. Non-cancellation
failures on the unclaimed (standalone probe) path still reap the parked
task, now with the reap failure logged instead of raising over the real
error.

Also maps mrz@mrzlab630.pw for the attribution check.

Co-authored-by: Adam Durham <amdnative@gmail.com>
2026-07-30 03:35:35 +05:30
Stepan Zadolia c00a1d58d5 fix(mcp): retain parked startup tasks for clean shutdown 2026-07-30 03:35:35 +05:30
Seppe Gadeyne ab0d3fac3d fix(mcp): keep drain and stop on loop thread 2026-07-30 03:35:35 +05:30
Seppe Gadeyne cac74e06c8 fix(mcp): bound loop-owned shutdown drain 2026-07-30 03:35:35 +05:30
shady cc21c4f78f fix(mcp): drain pending tasks before closing the MCP loop
_stop_mcp_loop() stopped and closed the background loop without reaping
the tasks still on it. A task left suspended is resumed later by the GC,
whose finalizer drives its cleanup against the now-closed loop:

    Exception ignored in: <coroutine object MCPServerTask.run ...>
      File "tools/mcp_tool.py", line 2947, in run
        parked = await self._wait_for_reconnect_or_shutdown(
      File "tools/mcp_tool.py", line 2161, in _wait_for_reconnect_or_shutdown
        t.cancel()
    RuntimeError: Event loop is closed

shutdown_mcp_servers() only reaps servers held in _servers, so a server
that parked after exhausting its initial-connect budget — never inserted
there, because start() raises _error before the caller registers it — has
no owner to signal it and stays suspended until the loop is gone.

Drain the loop the way asyncio.run() does: cancel the remaining tasks and
gather them while the loop is still open, so each runs its own finally.
Cancel alone is not enough — Task.cancel() only schedules the throw.

This resolves the reported traceback, but not the ownership bug that
strands the task in the first place; that needs a follow-up. Deliberately
not using "Fixes" so #60197 stays open for it.

Addresses #60197
Addresses #66113

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-30 03:35:35 +05:30
Gille 94d1dff50d fix(wake): route desktop control and select input devices 2026-07-29 14:04:21 -06:00
Ben Barclay f5b68ad58b Merge origin/main into feat/hsp-sync-client
Resolves the PR's conflict with main (2252 commits). Two conflicts, both
"each side added an independent block in the same place" — kept both:

- gateway/run.py — the housekeeping loop. This branch adds the Skill Sync
  pulls inside the CURATOR_EVERY branch (12-space indent); main adds a
  stale-session auto-archive as a sibling `if` at loop level (8-space).
  Different scopes, so the naive union would have mis-nested the archive
  block into the curator branch; kept each at its own indent level.
- tools/skill_manager_tool.py — the _edit_skill result dict. This branch
  appends the org auto-propose note; main appends
  _add_description_prompt_preview(). Independent, order-insensitive.

No behaviour dropped from either side.

Verified: 3552 passed / 0 failed across 63 suites (scope regenerated to
include main's new maybe_auto_archive / _add_description_prompt_preview
consumers) via scripts/run_tests.sh. `hermes sync` and `hermes sync status`
still work against a live token, resolving the production plane default.

The Pyright Optional-parameter warnings in skill_manager_tool.py are
pre-existing on main (`content: str = None` etc.), not introduced here.
2026-07-29 13:01:36 -07:00
Shizoqua 70411a6152 fix(cron): scrub ALL GitHub auth-header curl blocks, not just the first
Salvaged from #31671 (@Shizoqua). The config-cache half of that PR was
superseded on main (9b8b054c2d gave _load_config_safe a readonly path),
but this cron-scanner half is still live: _strip_cron_safe_constructs
used re.search + a single str.replace, which only scrubbed occurrences
IDENTICAL to the first match. A cron job loading several GitHub skills
carries heterogeneous auth-header curl forms (-H vs --header, quoting,
token var names) — every non-identical block tripped the
exfil_curl_auth_header detector on every tick, blocking legitimate
GitHub cron jobs.

Now re.sub scrubs every occurrence; the trailing [^\n]* consumes the
URL path so no dangling fragment remains. Sabotage-verified: the old
implementation false-blocks the heterogeneous two-skill prompt the new
regression test pins; exfil to a non-GitHub host is still blocked.
79/79 cron tool tests green.
2026-07-29 12:41:40 -07:00
Alex Fournier f1fd678e44 feat(observability): add Relay skill metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-29 12:20:34 -07:00
Alex Fournier 8502e464a8 fix(observability): harden tool lifecycle metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-29 12:20:17 -07:00
Teknium 8714040954 fix(computer_use): resolve gateway session-key namespace in permission-mode lookup
Follow-up to the #68246 salvage. The backend permission-mode resolution
only checked the DB session_id the tool path passes, but gateway /yolo
keys approval bypass off the gateway session_key (contextvar). Consult
both namespaces so /yolo works on messaging platforms, not just CLI/TUI.
Adds a regression test driving the real approval contextvar + yolo
toggle path E2E.
2026-07-29 12:19:37 -07:00
Francesco Bonacci c268397752 feat(computer_use): align cua-driver 0.10 permission modes 2026-07-29 12:19:37 -07:00
Francesco Bonacci 847e401b74 feat(computer_use): align cua-driver 0.9 contracts
Salvaged from PR #67807 by @f-trycua onto current main.

- Foreground gate: discover delivery_mode support from the live tools/list
  inputSchema.properties (fail closed), not the never-shipped
  input.delivery_mode capability token
- bring_to_front: standalone strict-schema MCP tool (inject_session=False),
  separate approval scope, requires foreground
- Verdict precedence: confirmed > unverifiable (verify before retry) >
  suspected_noop/refusal (escalate); surfaced as explicit verdict field
- Typed cua_browser_* route inside computer_use (browser_route.py) with
  exact-binding, adapter-injected session, snapshot-scoped refs
- Per-Hermes-session backend isolation + release_computer_use_session seam
  wired into AIAgent.close()
- Recorded 0.9 tools/list fixture replaces fabricated capability tokens
2026-07-29 12:19:37 -07:00
teknium1 5b751dc0ad chore: remove unused imports and dead locals (ruff F401/F841 sweep)
Cleans F401 unused imports and F841 dead local assignments across
root *.py, agent/, hermes_cli/, tools/, gateway/, cron/, tui_gateway/
(tests/, plugins/, skills/ excluded).

Intentionally KEPT (false positives / test-patch surfaces):
- agent/transports/__init__.py package re-exports
- cli.py browser_connect re-exports (DEFAULT_BROWSER_CDP_URL area,
  used by tests/cli/test_cli_browser_connect.py)
- hermes_cli/main.py _prompt_auth_credentials_choice /
  _model_flow_bedrock_api_key (accessed via main_mod attr in tests)
- gateway/run.py aliased replay_cleanup + whatsapp_identity re-exports
  and _PORT_BINDING_PLATFORM_VALUES (test-referenced)
- hermes_cli/web_server.py get_running_pid (tests monkeypatch it) and
  _OAUTH_TOKEN_URL availability probe
- hermes_cli/config.py get_process_hermes_home re-export (noqa'd F811
  chain) and yaml availability-probe import
- hermes_cli/nous_subscription.py managed_nous_tools_enabled
  (tests patch hermes_cli.nous_subscription.managed_nous_tools_enabled)
- try/except ImportError availability probes (env_loader, tts_tool,
  mcp_tool, web_server anthropic OAuth block)
- tools/web_tools.py noqa F401 re-exports
- hermes_cli/setup_whatsapp_cloud.py:263 'proceed' skipped: possible
  missing-guard bug, flagged for separate review
- unused function parameters (signature changes out of scope)

Side-effect RHS calls preserved where only the binding was dead
(e.g. web_server proc = _spawn_hermes_action -> bare call).
2026-07-29 11:53:39 -07:00
Teknium 16720dc45b fix(computer-use): hide the --no-overlay help probe console too
Follow-up to the #62821 salvage: the _cua_driver_supports_no_overlay
--help probe is another Windows-reachable spawn; give it the same
windows_hide_flags() treatment. Also adjust the status test to stub
_resolve_driver_cmd (permissions.py resolves via that helper, not
shutil.which).
2026-07-29 11:35:33 -07:00
motoblurr 7bc9956660 fix(computer-use): normalize Windows manifest paths in WSL
A Windows-installed cua-driver can return an absolute
``C:\Users\...\cua-driver.exe`` mcp_invocation.command to a Hermes
process running inside WSL. POSIX spawning can't use the raw Windows
string even though the binary is reachable through DrvFS. Translate
``<drive>:\...`` to ``/mnt/<drive>/...`` in _resolve_mcp_invocation
(before the path-separator check, since backslash is not a separator
on POSIX), only when actually running under WSL.

Salvaged from #63532 by @motoblurr (original commit carried a
placeholder 'Hermes Agent <hermes@local>' identity; re-authored).
Fixes #63938 premise.
2026-07-29 11:35:33 -07:00
ZundamonnoVRChatkaisetu 50e27abdd3 fix(computer-use): hide Windows cua-driver subprocess consoles
Apply windows_hide_flags() (CREATE_NO_WINDOW; 0 on POSIX) at the
Windows-reachable cua-driver subprocess boundaries: manifest probe,
update checker, CLI fallback transport, doctor health-report spawn,
and the permissions/status runner. Prevents OpenConsole/Windows
Terminal windows flashing into the foreground when spawned from
GUI-backed Gateway/Desktop processes.

The env-probe half of the original PR was already implemented on main
and is not re-applied here.

Salvaged from #62821 by @ZundamonnoVRChatkaisetu (original commits
carried a placeholder 'Claude Code Enterprise' identity; re-authored
to the contributor's GitHub identity).
2026-07-29 11:35:33 -07:00
Alex Fournier 8b0c3da8c0 feat(observability): aggregate bounded tool metrics 2026-07-29 11:25:55 -07:00
monerostar b9215f5bc9 fix(computer_use): surface CLI --version when health_report version lies 2026-07-29 11:09:08 -07:00
camaleonidas c6db7b0f4f fix(computer-use): fallback doctor when cua-driver health_report is unclassified
cua-driver 0.10.0 marks health_report as risk.class=unclassified and denies
the MCP call with isError. Hermes doctor previously treated the bare
{exit_code:1} structuredContent as a real report and printed
"cua-driver ? on ? — ?" with exit 1.

Detect isError / non-schema payloads, raise HealthReportUnavailable, and
compose a schema_version=1 report from working probes (check_permissions,
list_apps, CLI --version/doctor). Prefer real health_report when present.

Tests cover unclassified denial, schema preference, and overall mapping.
2026-07-29 11:09:08 -07:00
Andrew Chen 0411869503 fix(computer-use): block destructive key combos in hyphen notation
`_canon_key_combo` (the `_BLOCKED_KEY_COMBOS` gate in
`handle_computer_use`) split key strings on `+` only, but the cua-driver
backend's `_parse_key_combo` splits on both `+` and `-`. So a model could
issue `{"action":"key","keys":"ctrl-alt-delete"}` (or `alt-f4`,
`cmd-shift-q`): the gate saw a single unknown token and let it through
while the backend executed the real destructive shortcut.

Split the gate on both `+` and `-` so it canonicalizes combos the same
way the backend does. Non-destructive hyphen combos (`cmd-c`) and the
literal `-` zoom key (`cmd+-`) are unaffected.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-29 11:09:08 -07:00
Koho Zheng f2a4ca9637 fix(computer-use): normalize cua-driver result envelopes
cua-driver 0.7.x can return list_windows/list_apps payloads under
structuredContent.windows, data.windows, data._legacy_windows, or
top-level windows/_legacy_windows (direct CLI responses). The wrapper
only read structuredContent.windows, so discovery came back empty
(capture 0x0, list_apps []) while raw cua-driver calls worked.

- add _windows_from_tool_result(): walks the known envelope shapes in
  priority order, skipping empty higher-priority envelopes
- route _load_windows() (MCP + CLI re-fetch paths) through the helper,
  covering capture() and focus_app()
- harden _ingest_windows(): skip non-dict members, normalize untrusted
  app_name/title/z_index fields
- list_apps(): prefer structuredContent.apps, fall through populated
  data/top-level envelopes, derive unique apps from window-shaped
  payloads via _apps_from_windows(), keep the text-line fallback last
- tests for every envelope shape, precedence, malformed records, and
  app derivation

Salvaged from #63037 (Reaper-Legion), which itself preserved the
original implementation from #57961 (kohoj); #73007 (umi008)
independently proposed the same normalization later.

Fixes #57905

Co-authored-by: Reaper <248977840+Reaper-Forge@users.noreply.github.com>
Co-authored-by: Ulises Millan Guerrero <ulises.millanguerrero@gmail.com>
2026-07-29 11:08:58 -07:00
teknium1 bc747001ee perf(imports): lazy-load heavy SDKs off the cold-start waterfall
Four deferrals following the established truthy-skip / PEP 562
lazy-load patterns (PRs #22681/#22859 lineage). Rebased over #74194,
which independently landed the browser_tool half of this work — that
file is dropped here; the remaining four modules are untouched by it:

- tools/vision_tools.py: defer agent.auxiliary_client
  (credential_pool -> hermes_cli.auth -> httpx -> rich, ~50 ms) to
  first vision handler call. async_call_llm /
  extract_content_or_reasoning stay patchable module attributes;
  injected test mocks win over the loader.
- agent/model_metadata.py: defer 'requests' (+urllib3, ~27 ms of the
  'import cli' waterfall) to the fetch functions. PEP 562 __getattr__
  keeps patch('agent.model_metadata.requests.get') working.
- tools/browser_supervisor.py: websockets (~22 ms) imports on first
  CDP connect; ClientConnection type under TYPE_CHECKING.
- cron/jobs.py: croniter (~15 ms) resolves on first cron-expression
  use; HAS_CRONITER stays monkeypatchable (None = unprobed sentinel).

A/B vs current main incl. #74194 (median of 7, cold subprocess):
  import cli          147 -> 132 ms  (-10%)
  import model_tools  244 -> 224 ms  (-8%)
  import run_agent    264 -> 244 ms  (-8%)

Lazy-verify: importing the four modules no longer pulls requests /
croniter / websockets into sys.modules. 369 targeted tests green
post-rebase.
2026-07-29 10:54:04 -07:00
teknium1 ed33ebca1d refactor: canonical config loaders for behavioral reads + guarded raw-read primitive (kills the managed-scope/env-expansion drift class)
The disease: ~15 scattered raw yaml.safe_load(config.yaml) reads that
silently miss managed-scope overlay, ${ENV_VAR} expansion, profile-aware
pathing, and root-model normalization. Every new config feature needed an
N-site sweep (incident chain 9cbcc0c9c8 → 732293cf87 → b0e47a98f9 →
1928aa0443). This commit assigns every raw read to an owner and adds a
lint-guard test so the class cannot regrow.

New primitive (additive-only change to hermes_cli/config.py):
  read_user_config_raw(path=None) — reads the user file EXACTLY as
  written; docstring states it is ONLY legal for write-back round-trips
  and raw-file diagnostics. Behavioral reads must use
  load_config()/load_config_readonly().

BEHAVIOR FIXES (class-a sites migrated to a canonical loader — these
previously read values that could DIFFER from the effective config):

  gateway/run.py _try_resolve_fallback_provider → _load_gateway_runtime_config
    keys: fallback_providers/fallback_model (provider, model, base_url,
    api_key). Drift fixed: a managed-pinned fallback chain was ignored;
    an api_key of "${OPENROUTER_API_KEY}" reached the resolver unexpanded.
  gateway/run.py GatewayRunner._load_provider_routing → same loader
    key: provider_routing. Drift fixed: managed-pinned routing prefs and
    ${VAR} templates were ignored.
  gateway/run.py GatewayRunner._load_fallback_model → same loader
    keys: fallback chain. Same drift as above.
  gateway/run.py GatewayRunner._refresh_fallback_model
    keeps the raw primitive (its last-known-good-on-parse-failure contract
    forbids the fail-open loader, which returns {} on a torn write) but now
    applies managed overlay + env expansion inline. Drift fixed: chain
    edits under managed scope / env templates were previously frozen out.
  tui_gateway/server.py _load_cfg (72 behavioral call sites)
    now = raw read + managed overlay (pre-existing) + NEW ${VAR} expansion,
    split from a new _load_cfg_raw() write-back primitive. Drift fixed:
    e.g. custom_prompt: "hello ${VAR}", agent.system_prompt, model,
    api_key/base_url templates reached sessions unexpanded. DEFAULT_CONFIG
    is deliberately NOT merged (callers treat missing keys as unset;
    `_load_cfg() == {}` sentinels and _save_cfg round-trips depend on it).
  tui_gateway/server.py _profile_configured_cwd
    keys: terminal.cwd of a NON-launch profile. Drift fixed: managed
    overlay + ${VAR} expansion now apply (load_config() would resolve the
    wrong profile's home, so the raw primitive + inline pipeline is used).
  plugins/platforms/telegram/adapter.py _reload_dm_topics_from_config
    → load_config_readonly(). keys: platforms.telegram.extra.dm_topics.
    Drift fixed: managed overlay + profile-aware pathing + expansion.
  plugins/memory/holographic _load_plugin_config → load_config_readonly().
    keys: plugins.hermes-memory-store.*. Same drift class.

WRITE-BACK ROUND-TRIPS (class-b: stay raw BY DESIGN via read_user_config_raw;
merging defaults/overlay would pollute the saved user file):
  gateway/slash_commands.py: model persist x2, _save_gateway_config_key,
    memory/skills write_approval toggles
  gateway/platforms/yuanbao.py auto-sethome
  tui_gateway/server.py _write_config_key + all cfg→_save_cfg blocks
    (reasoning show/hide/full/clamp, details_mode[.section], prompt)
    → new _load_cfg_raw()
  plugins/memory/holographic save_config

RAW-FILE DIAGNOSTICS + presence-sensitive bridges (class-c: stay raw,
now via the shared primitive with an explanatory comment):
  hermes_cli/doctor.py x5 (model validation, stale-root-keys, .env drift,
    deprecation sweep, memory-provider probe — the latter two keep their
    inline managed overlay where they had one)
  gateway/run.py _bridge_max_turns_from_config and the module-level
    TERMINAL_*/HERMES_* env bridge (bridging merged defaults would export
    all of DEFAULT_CONFIG into the environment; both keep their inline
    overlay + expansion)
  hermes_cli/send_cmd.py env bridge (same presence-sensitivity)
  hermes_cli/gateway.py multiplex-conflict probe (reads the DEFAULT root's
    config, not the active profile's — load_config is the wrong owner)
  hermes_cli/profiles.py / hermes_cli/web_server.py / tools/wake_word.py
    multi-profile reads (load_config targets only the ACTIVE profile home)
  cron/jobs.py _resolve_default_model_snapshot and cron/scheduler.py
    run_job config read keep their existing inline overlay+expansion but
    now share the primitive (their fail-open + last-value semantics and
    the deliberate no-defaults merge are preserved exactly).

Failure-semantics audit: every migrated site preserves its exact previous
behavior on missing file ({} / early return) and parse failure (raise into
the caller's existing except, warn, last-known-good, or fail-open) —
read_user_config_raw intentionally mirrors bare open()+safe_load semantics
(raises on parse errors, {} only on FileNotFoundError/non-dict root).

Guard: tests/hermes_cli/test_config_read_guard.py scans the tree for
yaml.safe_load within 6 lines of a 'config.yaml' reference outside an
explicit ALLOWLIST (hermes_cli/config.py, gateway/config.py, gateway/run.py
fallback path, hermes_cli/managed_scope.py which reads the MANAGED file,
gateway/readiness.py parse-health probe) and fails on new offenders.

E2E: tests/hermes_cli/test_config_loader_e2e.py runs a subprocess with a
temp HERMES_HOME (config.yaml containing ${E2E_PROMPT_SUFFIX}) plus a
HERMES_MANAGED_DIR overlay pinning agent.reasoning_effort, asserting
tui _load_cfg resolves "hello world"/"high" while _load_cfg_raw +
_save_cfg round-trip the template and user value verbatim with no
managed/default leakage.
2026-07-29 10:53:29 -07:00
teknium1 3d48f893da refactor: single build_subprocess_env() factory for all child-process spawns (profile + secret-scrub single owner) 2026-07-29 10:14:11 -07:00
teknium1 1a7f73b8ea refactor: migrate hand-rolled error envelopes to shared tool_error()
Replace json.dumps({"error": ...}) boilerplate with the documented
tools/registry.py tool_error() helper across 13 files.

Migrated: 59 sites (58 code sites + 1 docstring example in
path_security.py), incl. multi-key envelopes passed via kwargs
(available_actions, path/already_read, pattern/already_searched,
parameters/hint, needs_reauth/server, error_type/tool/result_type).
Also removed 2 now-redundant local tool_error imports in mcp_tool.py
in favor of a module-level import.

Skipped (not byte/shape-compatible with tool_error):
- {"success": false, "error": ...} envelopes (browser_tool,
  browser_camofox, browser_dialog_tool, web_tools, tts_tool,
  skills_tool, image_generation_tool, project_tools, memory_tool,
  cronjob_tools, x_search_tool, xai_video_tools) — leading keys
  differ; key order would change.
- terminal_tool/code_execution_tool envelopes carrying output/
  exit_code/status leading keys.
- tool_search.py:912-area multi-key success paths (non-error).
- mcp_tool.py MCPSampling._error — returns MCP-spec ErrorData
  object, not a JSON string; incompatible.
- send_message_tool._error — returns a dict (not str) and applies
  secret redaction; return type must be preserved.

Behavior note: sites that previously omitted ensure_ascii=False now
emit raw UTF-8 (tool_error's canonical behavior) — JSON-equivalent.

Tests: 23 targeted files (tool_search, discord, file_tools/read
guards/operations, registry, clarify, homeassistant, code_execution,
send_message, delegate, terminal, mcp, model_tools, sanitize_tool_error,
retaindb plugin) — all pass. ruff clean.
2026-07-29 10:14:00 -07:00
teknium1 f57cb2e482 refactor: use utils atomic writes in cron/skill_manager 2026-07-29 10:13:50 -07:00
teknium1 7c198c5e44 refactor: single shared Retry-After parser 2026-07-29 10:13:50 -07:00
Teknium 5081551f09 fix(voice): full-duplex agent-turn listener — interrupt by voice during generation AND playback
Replaces the half-duplex per-playback barge monitors with ONE listener
that runs for the entire agent turn in continuous voice mode: armed at
utterance-submit, disarmed when the turn is fully done (response + TTS
finished). Fixes Teknium's live report that voice interruption never
works: (a) not while the LLM is generating, (b) not while TTS plays.

Root causes:
- HALF-DUPLEX GAP: the barge monitor only spawned when TTS playback
  STARTED (cli.py streaming/whole-file paths, gateway _tts_stream_begin).
  During LLM generation there was NO microphone listener at all.
- PLAYBACK DEAFNESS: the monitor calibrated its VAD noise floor WHILE the
  speaker was blasting TTS (speaker bleed baked into the floor), then
  multiplied it by 8x with a 1s strictly-consecutive block requirement —
  normal speech could rarely reach the trigger, and the 2s grace
  swallowed early interjections.

New model — tools/voice_mode.full_duplex_listen():
- Pre-playback calibration: quiet-room noise floor established at turn
  start and HELD through playback (never recalibrated against bleed).
- Phase-aware trigger: generation = floor x voice.barge_in_threshold_multiplier
  (new config, default 3.0, justified by synthetic-frame tests);
  playback = additionally clamped to a 1500-RMS minimum so bleed alone
  can't trip; 4000-RMS ceiling keeps speech always reachable.
- Windowed-majority detection (>=80% of a 300ms window) instead of the
  strictly-consecutive counter that reset on intra-word energy dips.
- Grace on playback ONSET only (voice.barge_in_grace_seconds, default
  down 2.0 -> 0.5) — suppresses the onset transient, not the mic.
- Debug diagnostics at every decision point (calibrated floor, per-window
  RMS above 50% of trigger, trip/no-trip, grace suppressions) — always
  logger.debug, mirrored to stderr under HERMES_VOICE_DEBUG=1.

Phase behavior (CLI cli.py + tui_gateway/server.py, same model):
- generation: speech interrupts the in-flight turn via the SAME seam the
  typed/Ctrl+C interrupt uses (agent.interrupt()), cuts any pending TTS
  pipeline so the stale reply never plays, and submits the captured
  interjection (pre-roll capture, first syllable kept) as the next turn.
- playback: cuts TTS (streaming pipeline stop + fallback speak stop
  events + file player) and submits the capture.
- stop phrase honored in BOTH phases: mid-generation 'stop' interrupts
  the turn AND ends the voice chat (stop everything).
- one listener instance spans generation -> playback (no re-arm race);
  double-arm refused (CLI _voice_fd_active / gateway _fd_listener_active).

Gateway specifics: _arm_full_duplex_listener() at _run_prompt_submit turn
start and inside _tts_stream_begin; _speak_text_with_barge registers its
(stop, done) pair in _fd_speak_pipelines so fallback speaks are cut and
tracked; _tts_stream_barge_in_monitor kept as a shim that arms the new
listener. Desktop renderer owns its own mic path (voice-barge-in.ts) and
is unaffected; if desktop backend-mic mode is used it inherits via the
gateway.

Tests: full_duplex_listen synthetic-RMS suite (speech-over-bleed trips,
bleed alone doesn't, quiet floor held through playback, grace window,
multiplier math 3x vs 8x, windowed-majority dips), CLI listener phase
tests (generation interrupt seam, playback cut, lifecycle spans phases,
double-arm, config forwarding, stop-phrase-mid-generation), gateway
generation-phase interrupt + stop-phrase tests. Generation-interrupt
test sabotage-verified.
2026-07-29 10:08:53 -07:00
teknium1 490056d6d3 perf: lazy mcp SDK import + tool-discovery mtime cache + browser_tool import diet
Three cold-start cuts, measured with .venv python, PYTHONPATH=worktree,
median of 3-5 fresh subprocesses:

1. tools/mcp_oauth.py — availability now via importlib.util.find_spec("mcp");
   SDK classes (OAuthClientProvider et al.) import lazily on first use via
   _ensure_sdk_loaded(). Module-level names kept as None placeholders so the
   test-patch surface (patch.object(mcp_oauth, "OAuthClientProvider", ...))
   still works. import tools.mcp_oauth: 242ms -> 56ms (mcp SDK no longer
   loaded at import time).

2. tools/registry.py — discover_builtin_tools AST scan memoized in an
   mtime_ns+size-keyed disk cache at ~/.hermes/cache/tool_discovery_cache.json
   (atomic write via utils.atomic_json_write, best-effort/never raises;
   corrupt or missing cache -> full rescan + rewrite; per-file stat mismatch
   -> rescan just that file). Scan of 100 files: 158ms cold -> 3ms warm.

3. tools/browser_tool.py — top-level `import requests` and
   agent.auxiliary_client.call_llm moved to lazy first-use (PEP 562
   __getattr__ preserves patch("tools.browser_tool.requests.get") and
   patch("tools.browser_tool.call_llm") surfaces; internal call sites go
   through _lazy_call_llm which reads module globals so patches are honored).

Entry-point imports (median ms, before -> after):
  import model_tools   392 -> 245   (warm discovery cache)
  import cli           152 -> 151   (unchanged; cli doesn't hit these paths)
  import gateway.run   234 -> 230

Functional verification:
- get_tool_definitions(quiet_mode=True) under temp HERMES_HOME: identical
  sorted 30-tool name set before vs after (empty diff).
- Discovery cache: delete cache -> 158ms, second run -> 3ms; corrupt cache
  -> clean full rescan; touching one file -> single-file rescan (12ms).
- Tests green: tests/tools/test_registry.py, all test_mcp_oauth*,
  test_mcp_dashboard_oauth, test_mcp_tool_401_handling, all
  tests/tools/test_browser*.py, tests/hermes_cli/test_mcp_{config,startup,
  dashboard_oauth}.py, test_skills_tool_discovery_cache.py.
2026-07-29 10:02:03 -07:00
teknium1 19055492aa fix: route stray HERMES_HOME hardcodes through get_hermes_home() (profile + native-Windows safety) 2026-07-29 09:33:48 -07:00
victor-kyriazakos 1773752c8c Merge remote-tracking branch 'origin/main' into feat/gateway-health-diagnostics-monitoring
# Conflicts:
#	uv.lock
2026-07-29 15:37:14 +00:00
Teknium df093bf33c feat(voice): calm ambient "thinking" sound while the agent works in voice chat
Long thinking/tool stretches in a voice conversation are dead air — the
user cannot tell whether the agent is alive. New: quiet, repeating soft
bubble blips while the agent works and no speech audio is flowing.

- tools/voice_mode.py: numpy-synthesized blips (no binary assets) — two
  alternating low pitches (G4/E4) with pitch glide + smooth attack/decay
  envelopes, ~0.8-1.2s randomized spacing, volume = voice.beep_volume * 0.5.
  start_thinking_sound(should_play=...) / stop_thinking_sound() daemon-loop
  lifecycle; macOS-TCC-safe (sounddevice output gated there → silent skip,
  no per-second afplay churn). New mark_audio_output_active()/
  is_audio_output_active() ref-count wraps play_audio_file and the
  streaming OutputStream sentence writes so "audio is flowing" is accurate.
- Config: voice.thinking_sound (default true) off-switch.
- cli.py: starts when a voice-mode turn begins, per-blip gate skips while
  TTS speaks / mic records / barge capture owns the mic; stopped in the
  chat() finally on every exit path.
- tui_gateway/server.py: same lifecycle around _run_prompt_submit turns
  (voice mode on), gated on is_audio_output_active + continuous capture.
- Desktop: renderer owns voice-conversation audio, so a matching WebAudio
  implementation (src/lib/thinking-sound.ts, same envelope/pitches) runs
  while conversation status === "thinking"; honors voice.thinking_sound
  (via config store) and the shared sound-mute toggle; stops instantly on
  speaking/listening/end.
2026-07-29 08:24:00 -07:00
Teknium 6fdfdc1597 feat(voice): "Say <stop-phrase> to end the voice chat" notice on voice-mode start (CLI/TUI/desktop, i18n)
One owner for the wording: voice_stop_hint() in tools/voice_mode.py —
sources the phrase from voice.stop_phrases (first entry) so a custom
phrase renders correctly, and returns "" when the feature is disabled
(stop_phrases: []) so no surface shows a hint.

- CLI: printed in /voice on output (style-matched dim notice).
- TUI: voice.toggle action=on now carries stop_hint; the Ink client
  renders it in the "Voice mode enabled" block (older gateways omit
  the field — no hint, no crash).
- Desktop: the renderer voice loop never touches tools/voice_mode.py,
  so the phrase is read from config (voice.stop_phrases → $voiceStopPhrase
  store, seeded in use-hermes-config) and shown as an info toast when a
  voice conversation starts. i18n: en/ja/zh/zh-hant/ar.
2026-07-29 08:24:00 -07:00
beardedeagle be424703c4 fix(voice): rolling-window VAD, duplicate render suppression, TUI gateway mirror
Replace one-shot VAD calibration with a rolling deque window that
continuously recalibrates the noise floor throughout TTS playback,
preventing false barge-in triggers from stale calibration. Add a
grace period before VAD activates so TTS playback establishes first.
Suppress duplicate text rendering when token streaming is enabled.
Mirror the barge-in and TTS stream stop logic to the TUI gateway path
so both CLI and gateway use the same VAD semantics.

Rolling-window VAD:
- 90th percentile of rolling window (~3s) for noise floor
- 8x multiplier (was 5x) for TTS volume variation headroom
- 4000 RMS trigger ceiling so genuine speech can still trip
- min_floor clamped to SILENCE_RMS_THRESHOLD * 2
- sustained_ms=1000, calibration_ms=800

Barge-in grace period (barge_in_grace_seconds, default 2.0s):
Delays VAD activation so TTS playback establishes before the mic opens.

Duplicate render suppression:
When streaming_enabled, pass display_callback=None to
stream_tts_to_speaker so the token stream is the sole display path.

TUI gateway mirror:
Mirror _tts_stream_stop and _tts_stream_barge_in_monitor changes to
tui_gateway/server.py so both code paths use the same VAD parameters,
grace period, and TTS CUT diagnostic logging.

Profile-scoped session DB and MoA progress events in tui_gateway/server.py
were necessitated by the TTS pipeline changes affecting session state
and event routing.

Normal-exit flag and TTS CUT diagnostic logging at all cut paths.

Regression tests:
- test_quiet_then_loud_playback_does_not_trip
- test_8x_multiplier_absorbs_tts_volume_spikes
- test_trigger_ceiling_lets_genuine_speech_trip
- test_silence_calibration_does_not_false_trip_on_tts
- test_tts_stream_stop_latches_interruption_for_next_turn
- test_tts_stream_stop_after_natural_finish_does_not_latch
- Profile-scoped session DB tests (10 tests)
2026-07-29 08:24:00 -07:00
Ben Barclay e327eaa2a0 feat(sync): default the sync plane to production
Skill Sync had no default base URL, so a user with no `sync.base_url` in
config.yaml and no HERMES_SYNC_BASE_URL got:

    sync inert: no sync base URL configured (config.yaml sync.base_url
    or HERMES_SYNC_BASE_URL).

Every sync command was unusable out of the box. The URL was left unset
because the plane did not exist yet when the client was written; it does now.

- Adds DEFAULT_SYNC_BASE_URL = "https://gateway-gateway.nousresearch.com" and
  returns it as the last step of resolve_sync_base_url().
- Resolution order is unchanged otherwise: HERMES_SYNC_BASE_URL ->
  config.yaml sync.base_url -> production default. The env var and config key
  now exist to point a dev/staging build at another plane rather than to make
  the feature work at all.
- Follows the existing precedent for production endpoints in this codebase
  (DEFAULT_NOUS_PORTAL_URL in hermes_cli/auth.py, HERMES_DIAGNOSTICS_BASE_URL
  in diagnostics_upload.py): a module constant with env/config override.

The "no sync base URL configured" guards are kept — they are now unreachable
in practice but remain correct if the default is ever blanked.

Tests: 3 new — the default is returned when nothing is configured, config
still overrides it, and the constant is a bare https origin (no trailing
slash, no path) since the client appends /v1/sync/. 2349 passed / 0 failed
across 56 suites via scripts/run_tests.sh.

Verified against a temp HERMES_HOME with no config: resolves to the
production plane; HERMES_SYNC_BASE_URL and sync.base_url both still win, and
trailing slashes are stripped.
2026-07-29 08:14:03 -07:00
kshitij kapoor 22492f0c46 refactor: extract atomic_write_text to utils.py; fix write-failure error handling
Deduplicates the mkstemp→fsync→atomic_replace pattern that existed in
three places: agent_import.py (added by #72983), MemoryStore._write_file,
and skill_manager_tool._atomic_write_text. All three now call a single
utils.atomic_write_text helper.

Also wraps the atomic_write_text call in _merge_memory_entries with
try/except OSError so a write failure records a per-item error instead
of propagating uncaught and aborting the entire import with no record.

Follow-up to #72983.
2026-07-29 16:49:07 +05:30
Teknium bf8004e3a8 fix(stt): kill faster-whisper silence hallucinations at the source
Local faster-whisper called model.transcribe with bare {'beam_size': 5}:
no VAD, cross-window conditioning on, no confidence filtering. Pure
silence produced hallucinated tokens (E2E: 5s anullsrc WAV -> 'You',
no_speech_prob=0.705) and noisy clips could produce runs of junk, often
in other languages.

Three-layer class fix, one shared owner for every local-whisper call
site (build_local_transcribe_kwargs):

1. Silero VAD filter (bundled with faster-whisper) on by default —
   silence never reaches the model. stt.local.vad: false restores the
   raw behavior for music/ambient transcription.
   stt.local.vad_min_silence_ms tunes chunk splitting (default 500).
2. condition_on_previous_text=False — one hallucinated token can no
   longer seed a self-reinforcing run; negligible cost for
   voice-note-length audio.
3. Segment confidence gate (_join_confident_segments): drop a segment
   only when no_speech_prob > 0.6 AND avg_logprob < -1.0 (openai-whisper's
   own heuristic shape; both must hit so quiet-but-real speech survives).
   Config: stt.local.no_speech_prob_threshold / logprob_threshold.

The WHISPER_HALLUCINATIONS blocklist in voice_mode.py stays as
last-resort defense but should now almost never fire.

E2E (real faster-whisper 'base', CPU int8):
  silence.wav  before 'You'                        -> after ''
  noise.wav    before ''                           -> after ''
  speech.wav   before/after 'Hello World, this is a test of the
               transcription system.' (unchanged)

Docs (EN + zh-Hans), DEFAULT_CONFIG, cli-config.yaml.example updated;
19 unit tests (kwargs contract, off-switch, confidence gate incl.
quiet-speech survival, _transcribe_local wiring), sabotage-verified.
2026-07-29 00:01:33 -07:00
Teknium ba13132298 fix(voice): bare stop phrase ends the voice chat on every surface, spoken or typed
Saying OR typing a configured stop phrase (voice.stop_phrases, default
"stop") now ends the voice chat everywhere, not just classic CLI PTT:

- hermes_cli/voice.py: new explicit on_stop_phrase callback through
  start_continuous/stop_continuous. The force-transcribe path previously
  DISCARDED the stop phrase silently — with auto_restart=False the client
  re-arms the next capture, so the conversation never ended. Both halt
  paths now fire on_stop_phrase (fallback: on_silent_limit for legacy
  callers) as user intent, distinct from the no-speech timeout.
- tui_gateway/server.py: voice.record wires on_stop_phrase and emits
  voice.transcript {stop_phrase: true} after flipping HERMES_VOICE(_TTS)
  off and stopping streaming TTS — same teardown as /voice off. The TTS
  barge-in monitor stop-checks its transcript too. prompt.submit consumes
  a TYPED bare stop phrase at the server-side choke point when voice mode
  is on (returns {voice_stopped: true}, no turn starts).
- ui-tui: voice.transcript {stop_phrase} ends voice mode with a clear
  'voice chat ended' notice (distinct from the no-speech-limit message);
  submitPrompt releases the busy latch on a consumed voice_stopped reply.
- cli.py: _typed_voice_stop in process_loop — typing a bare stop phrase
  while voice mode/continuous is active ends voice mode instead of
  sending 'stop' to the agent; typed 'stop' outside voice mode is
  unchanged. Voice transcripts skip the check (already stop-checked).
- desktop: interceptsTypedVoiceStop — the composer's onSubmit ends the
  live voice conversation (same path as clicking end on the pill) when a
  bare stop command is typed with no attachments; renderer-owned loop, so
  handled client-side like the existing spoken isVoiceStopCommand.
- tools/voice_mode.py: transcribe_recording never lets the Whisper
  hallucination filter swallow a configured stop phrase (e.g. 'bye'
  configured as a stop phrase is both a hallucination-blocklist entry and
  a stop phrase — stop-phrase check now wins).

Tests: continuous-loop signal (sabotage-verified), force-transcribe stop
signal + legacy fallback, hallucination-filter ordering, typed-stop CLI
unit tests (voice on/off/longer text), prompt.submit typed-stop gateway
tests, TUI vitest for stop_phrase event handling, desktop vitest for the
typed-stop interceptor.
2026-07-29 00:01:06 -07:00
Teknium 158e9a9977 refactor: remove the claude-marketplace skill source (redundant Marketplace hub tab)
The Skills Hub 'Marketplace' tab showed a single useless entry: Anthropic
changed .claude-plugin/marketplace.json to bundle-shaped plugins whose
source is './', so all plugins collapsed to one identifier pointing at the
repo root, and the second marketplace repo (aiskillstore/marketplace) is
gone (404). Everything in anthropics/skills is already surfaced by the
GitHub tap as the Anthropic tab, making this source fully redundant.

Removes ClaudeMarketplaceSource and all wiring: source router, index
builder (crawl + floors + sort order + rate-limit messaging), extract
labels/install/URL mapping, hub UI tab, web server labels, CLI limits,
docs (en + zh), the legacy index-cache snapshot, and test fixtures.

Stale skills-index entries with source 'claude-marketplace' still install
fine: HermesIndexSource fetches via resolved GitHub paths generically.
2026-07-28 23:16:27 -07:00
Teknium 805c1c340c feat(stt): support OpenAI gpt-transcribe transcription model
Adds gpt-transcribe (OpenAI's new file-transcription model, $0.0045/min)
to the OpenAI STT provider:

- OPENAI_MODELS set: gpt-transcribe is recognized so provider
  auto-correction keeps it on OpenAI and rejects it on Groq
- Language hint wiring: gpt-transcribe replaces the singular
  'language' field with a 'languages' list; the API rejects the legacy
  field, so the hint is sent via extra_body {languages: [..]}
- Config comment (DEFAULT_CONFIG), cli-config.yaml.example, desktop
  settings enum, and docs (en + zh-Hans) updated
- Tests: model pass-through, languages-list hint shape, legacy singular
  hint preserved for gpt-4o-transcribe, Groq auto-correction

gpt-live-transcribe (realtime WebSocket, $0.017/min) is NOT wired here:
the file-based STT pipeline has no realtime session path; it belongs in
a future realtime/voice-mode integration.
2026-07-28 22:40:45 -07:00
Shannon Sands 8bbd77f368 fix: route memory-provider dep installs through lazy_deps durable target
Installing a memory provider (Honcho, mem0, hindsight, ...) from the
dashboard Plugins page failed on hosted deployments with a permission
error: the setup endpoint shelled out to
`uv pip install --python sys.executable`, which targets the sealed
read-only venv under /opt/hermes (immutable hosted image, NS-579/#49113).

The correct mechanism already exists: tools/lazy_deps.py redirects
installs to the writable durable target on the data volume
(HERMES_LAZY_INSTALL_TARGET=/opt/data/lazy-packages) when the venv is
sealed (HERMES_DISABLE_LAZY_INSTALLS=1), appends the target to the END
of sys.path (core venv always wins collisions), and constrains shared
deps to core-venv versions. The dashboard installer simply never used
it.

Fix:
- tools/lazy_deps.py: new public install_specs() — installs arbitrary
  manifest-declared pip specs through the same environment routing as
  ensure(): venv-scoped by default, durable-target on sealed images,
  refused with an actionable reason when gated off (config kill switch
  or sealed venv without a target — never surfaces raw EROFS/EACCES).
  Specs are validated with _spec_is_safe(); post-install it invalidates
  import/metadata caches so availability rechecks in the same process
  see the new packages without a restart. Never raises.
- hermes_cli/web_server.py: _install_memory_provider_pip_dependencies
  now calls install_specs() instead of building its own uv/pip
  subprocess. Blocked installs surface the gate reason in the setup
  results; the response's status block reflects post-install
  availability (stale 'missing deps' state clears immediately).
- hermes_cli/memory_setup.py, plugins/memory/honcho/cli.py,
  plugins/memory/mem0/_setup.py: CLI setup wizards routed through
  install_specs() too — same sealed-venv failure mode, same fix.

No hosted setup path writes to /opt/hermes anymore; provider discovery
and installation now use the same environment (sys.path activation is
shared with the lazy-install bootstrap in hermes_bootstrap).

Tests:
- tests/tools/test_lazy_deps.py: TestInstallSpecs — gating matrix
  (sealed+no-target blocked with immutable-deployment reason, config
  kill switch, sealed+target proceeds), spec-safety rejection before
  any subprocess, venv-scoped vs --target command display, failure
  stderr passthrough, never-raises contract.
- tests/hermes_cli/test_web_server.py: setup endpoint routes pip
  through lazy_deps (regression guard asserts no direct 'pip install'
  subprocess), blocked-reason surfacing, same-response availability
  recheck clears stale missing state.

Fixes NS-605 (Plain T-1111).
2026-07-28 22:40:33 -07:00
Teknium 7800bb1a29 fix(tts): route streaming-provider secrets through resolve_provider_secret; bound per-sentence stream bodies at 16 MiB
Follow-up integration for the #47588 salvage, aligning the new streamers
with the post-campaign invariants:

- All streaming key lookups go through _resolve_key -> tts_tool.
  _resolve_provider_key -> resolve_provider_secret (config > env/.env >
  credential pool, profile-scoped) — never bare get_env_value. xAI
  resolves via resolve_xai_http_credentials so OAuth users stream too.
- _capped(): every provider's chunk iterator is bounded at 16 MiB per
  sentence, mirroring _read_tts_response_bytes' bounded-upstream-body
  invariant on the sync paths.
- Tests updated for the resolver contract + new coverage for credential
  routing and the cap.
2026-07-28 22:31:40 -07:00
Carlos Diosdado bc4dcb1b02 feat(tts): Gemini SSE + xAI WebSocket streaming providers, tts.streaming.provider knob, docs + E2E tests
Salvaged from PR #47588 and rebased onto the post-campaign streaming core:
the StreamingTTSProvider ABC/registry and the ElevenLabs/OpenAI streamers
already live on main (tools/tts_streaming.py), so this ports the pieces
main lacked:

- GeminiStreamer: streamGenerateContent?alt=sse -> base64 PCM chunks
  (24 kHz mono int16), reusing main's DEFAULT_GEMINI_TTS_* constants.
- XAIStreamer: WebSocket wss://api.x.ai/v1/tts -> binary PCM frames,
  async->sync bridged via the _collect_async test seam.
- tts.streaming.provider config knob: pin one streamer, or 'auto' to
  walk the priority list elevenlabs -> gemini -> openai -> xai. Unset
  keeps the never-swap-the-user's-voice default.
- docs/streaming-tts.md: architecture, capability matrix, how to add
  a provider.
- Unit tests for the knob, SSE parsing, and the WS bridge; key-gated
  E2E tests (skipped without credentials).

Refs: #47588
2026-07-28 22:31:40 -07:00
Teknium 0f64557c06 fix(wake): coerce dead onnx->tflite on macOS ARM64; clear stale voice turn-timeout
Two follow-ups from the voice PR (#70509).

1. macOS ARM64 onnx migration. Existing users who pinned
   openwakeword.inference_framework=onnx before the tflite fix landed kept a
   wake word that arms but never fires (ONNX's embedding model is broken on
   Apple Silicon, upstream #336). New resolve_inference_framework() honors an
   explicit framework everywhere ONNX actually works, but coerces the one
   provably-dead combination (explicit onnx + macOS ARM64) to tflite with a
   one-time warning. No config mutation; empty still falls back to the platform
   default. Both read sites (engine init + requirements check) route through
   the shared resolver.

2. Voice turn-timeout leak. Each listen cycle reassigned turnTimeoutRef
   without clearing the prior 60s timer, so a stale timer from an earlier
   cycle could fire handleTurn() mid-way through a later listen — after enough
   idle re-listens this wedged the loop into a non-re-arming state (the
   'voice chat deactivates after ~a minute' report). Clear before re-arm.

Tests: 64 wake tests (added onnx-coercion / intel-kept / tflite-kept /
empty-default cases; updated the stale 'explicit onnx kept on ARM64' test
that encoded the old broken behavior), 39 desktop voice/wake vitest, tsc +
eslint clean.
2026-07-28 19:40:25 -07:00
Teknium f041c95b7f fix(send_message): pass photon DM chat GUIDs through as explicit targets
'photon:any;-;+1555...' targets matched no parser pattern, so
_handle_send bounced them off the channel directory and failed
resolution even though the adapter accepts the GUID verbatim (the
react handler already passed them through). Recognize the DM chat
GUID shape (mirrors the adapter's _DM_CHAT_GUID_RE) in
_parse_target_ref for photon only.
2026-07-28 18:21:01 -07:00
Teknium 050461ec83 fix: hoist STT credential read guard to the public transcribe_audio entry point
The rebase onto #73510's prepare/dispatch split left the guard inside
_transcribe_prepared_audio, where source validation ran first and a
blocked .env surfaced a format error instead of the read-block message.
Guard now fires before any validation/preprocessing.
2026-07-28 18:12:26 -07:00
Teknium e251e78df9 feat(tools): env_passthrough allowlist for command-provider secret scrub
Command providers legitimately reference their own API keys in shell
templates (curl one-liners). The #70342 scrub removes ALL provider keys,
which would break such setups. Add a per-provider env_passthrough list
(TTS + STT) that copies named variables back from the parent env, plus
docs and tests. Scrub stays the default; passthrough is explicit opt-in.
2026-07-28 18:12:26 -07:00
Teknium fc26e965bb fix(tools): apply idle timeout to command STT runner (class fix for #50081)
Port the progress-based idle-timeout pattern from _run_command_tts
(PR #50087, @CleanDev-Fix) to _run_command_stt: the timeout resets on
any stdout/stderr output, so a slow-but-alive STT provider survives
while a silently stalled one is killed. Stuck detection stays
progress-based, never wall-clock.
2026-07-28 18:12:26 -07:00
Frowtek 38bb193f38 fix(stt): route transcription inputs through the shared read guard
`transcribe_audio` reads a local file and hands it to the configured STT
provider — for the hosted providers (Groq, OpenAI, Mistral, xAI, ElevenLabs)
that ships the file's bytes to a third-party API. The same local-input read
guard was added to image-gen (587be5b5b) and xAI video-gen (104232979) to keep
the agent from feeding credential/secret stores to a provider, but STT was
missed.

Call `get_read_block_error(file_path)` at the top of `transcribe_audio`, before
validation/dispatch, so a `.env`, `auth.json`, `.anthropic_oauth.json`,
`mcp-tokens/`, etc. is refused up front instead of being transcribed (and, for
hosted providers, exfiltrated). This is defense-in-depth, not a security
boundary — the guard's own message says so — but it restores parity with the
image/video-gen tools.

Regression test: a `.env` file is refused with the shared read-guard message
before any provider dispatch (mutation-verified).
2026-07-28 18:12:26 -07:00
dsad 37d0b6c81a fix(tts): block output to protected paths 2026-07-28 18:12:26 -07:00
Eugeniusz Gilewski b76acacbb9 fix(tools): execute local STT templates without a shell
HERMES_LOCAL_STT_COMMAND rendered quoted placeholders into a
user-configured template and passed the result to shell=True. Shell
metacharacters in the template therefore remained executable syntax even
though the placeholder values themselves were quoted.

Tokenize the rendered template and invoke it as an argv list while
preserving the existing timeout, closed stdin, and Windows creation flags.
Lock the invocation contract with metacharacter regression coverage and
document explicit shell wrapping for trusted templates that need it.

Salvages #32694

Co-authored-by: Ernest Hysa <takis312@hotmail.com>
2026-07-28 18:12:26 -07:00
Sherman 273b986fd9 feat(tools): expand command TTS output_format allowlist (m4a/aac/amr/opus)
Command-type TTS providers validated output_format against a hardcoded
{mp3,wav,ogg,flac} set; any other value was silently coerced back to mp3,
which then mismatched the output path the post-run check expects. This
blocked common ffmpeg-producible containers/codecs — notably m4a (AAC),
the portable choice for WeChat/iOS/mobile voice files — with no
config-only path (only a local source patch, lost on every update).

Widen COMMAND_TTS_OUTPUT_FORMATS to add m4a, aac, amr, opus. This only
permits a command provider to declare these; the user's command still
produces the file (e.g. via ffmpeg). No built-in provider behavior
changes and no new required config.

Update the two tests that pinned the old set, and add a positive case
covering the new formats. Document the supported output_format values.
2026-07-28 18:12:26 -07:00
峯岸 亮 3ae25e0fbd fix(security): scrub credentials from voice playback subprocesses
## Summary
- Spawn system audio players (`ffplay` / `afplay` / `aplay`) with `hermes_subprocess_env(inherit_credentials=False)`.
- Prevent gateway tokens and provider API keys from leaking into OS media helpers.
- Add a regression test asserting scrubbed env on `Popen`.

## Salvage / credit
Sibling of #70342 / incomplete #56332 (TTS/STT command scrub) on the voice-mode playback path.
2026-07-28 18:12:26 -07:00
峯岸 亮 24a6fb6448 fix(security): scrub Hermes secrets from voice command subprocess env
Salvage incomplete #56332: route command TTS/STT through hermes_subprocess_env
while preserving delegated-child lineage, and close the sibling local-whisper
subprocess.run path that still inherited the full process environment.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-28 18:12:26 -07:00
CleanDev-Fix 4e8a66dace fix(tools): keep command TTS deadline through exit 2026-07-28 18:12:26 -07:00
CleanDev-Fix 1b97e3efc5 fix(tools): chunk command TTS stream reads 2026-07-28 18:12:26 -07:00
CleanDev-Fix 3884f078bd fix(tools): use idle timeout for command TTS 2026-07-28 18:12:26 -07:00
Teknium 7e7f7d3059
Merge pull request #70509 from NousResearch/hermes/hermes-29661bf6
feat(voice): on-device wake words with open-vocabulary phrases and multi-profile voice routing
2026-07-28 17:58:33 -07:00
Atakan 20de37d409 fix: reject ambiguous MCP tool name collisions 2026-07-28 15:02:52 -07:00
Ben Barclay f9c4d835f9 refactor(sync): name the access gate for what it is (Nous admin)
The client called its gate "the DEV-PHASE gate (tool_gateway_admin)", which
reads as though Skill Sync is gated on an unrelated service's admin right.
It isn't. NAS populates that claim from Permissions.ADMIN_ACCESS — the global
portal admin permission that guards /admin/* — so the gate is "is this user a
Nous admin?". The claim is simply named for its first consumer, the tool
gateway.

Renamed on this side to say what it means, while keeping the wire string
(other services read it):

- DEV_GATE_CLAIM -> NOUS_ADMIN_CLAIM (value unchanged: "tool_gateway_admin",
  with a comment recording why the wire name differs).
- identity/status key dev_gate_ok -> nous_admin, across the client, the CLI
  consumers, and the tests.
- The module docstring now states where the claim comes from, that the wire
  name is misleading, and that this gate is pre-launch containment rather
  than the shipping entitlement — admin status conflates "may administer
  Nous" with "has Skill Sync enabled" and has no middle setting for a beta
  cohort. Choosing the real entitlement is left as a separate decision.

Naming only — no behaviour change, and no change to which accounts can sync.
The user-facing messages stay deliberately vague ("not enabled for your
account yet") rather than telling users they need portal admin.

Verified: 2346 passed / 0 failed across 56 suites via scripts/run_tests.sh;
`hermes sync status` against a live token reports "nous_admin": true. Zero
stale dev_gate_ok / DEV_GATE_CLAIM references remain.
2026-07-29 07:57:25 +10:00
Ben Barclay 4f990ec09e refactor(sync): put every Skill Sync verb under `hermes sync`; drop HSP naming
Encapsulates the feature behind one command for launch, and adopts the
official product name.

One command:
- `propose` moves from `hermes skills propose` to `hermes sync propose`, so
  the whole feature is one command to learn and one to document. Its handler
  moves from cmd_skills to cmd_sync accordingly.
- The `hermes sync` parser now documents both halves plainly: personal sync
  across your devices, and sharing with your organisation. Added an examples
  epilog; rewrote the verb help in user language ("Include a skill in your
  sync" rather than "Opt a skill into sync").
- Every user-facing string that pointed at `hermes skills propose` now points
  at `hermes sync propose` (8 sites, including the agent-visible guidance
  returned by skill_manage and the org provenance header).

This also clears the way for #39343, which adds its own top-level `sync` for
git-repo profile backup — that feature nests under `skills`, this one owns
`sync`.

Naming:
- HSP / "Hermes Sync Protocol" is gone from prose, docstrings, and comments.
  The feature is "Skill Sync".
- Public identifiers renamed: HSPClient -> SyncClient, HSPError -> SyncError,
  HSPConflict -> SyncConflict, hsp_address -> wire_address, HSP_VERSION ->
  WIRE_VERSION.
- The WIRE names are deliberately NOT renamed: the `hsp_version` capability
  field and the `x-hsp-object-type` response header are set by the deployed
  gateway-gateway sync plane (verified in src/sync/syncRouter.ts), so
  renaming them client-side would break sync against a live server. A comment
  at the version constant records why they differ from the product name.
- The version-mismatch error is now actionable ("this server speaks sync
  version X, but this Hermes speaks Y — update Hermes to sync with it")
  instead of leaking the protocol acronym.

Also fixes a wiring gap found on the way: the gateway housekeeping tick
pulled personal skills but never org skills — the same defect already fixed
for the CLI. Org pull now runs there too, gated on real org membership.

Tests: the jargon guard now also fails on a bare "HSP". The two tests that
asserted the old cross-command structure are replaced by three asserting the
new one (propose IS under sync, propose is NOT under skills, sync usage
lists it). 2294 passed / 0 failed across all 51 suites that import the
changed modules, via scripts/run_tests.sh.

Verified by running the real CLI: `hermes sync --help` lists all eight verbs,
`hermes skills --help` no longer mentions propose, `hermes sync propose
--help` parses, and `hermes sync status` still reports live org state.
2026-07-29 07:47:06 +10:00
Atakan 9dcb44a219 fix(schema): preserve dependentRequired property names 2026-07-28 14:37:19 -07:00
Teknium 8151670712 fix(mcp): widen discovery lock wait to cover real discovery durations
The bounded lock wait was 10 x 0.2s = 2s, but the concurrent-discovery
scenario this lock exists for (#62771: hermes serve + gateway spawning
every MCP server twice) reports 40-60s discovery rounds. A 2s budget
guarantees the loser times out and runs unguarded exactly when the guard
matters. Widen to 240 x 0.5s = 120s; fail-soft unguarded fallback and
test overrides unchanged.
2026-07-28 14:31:24 -07:00
Atakan 362fc21577 fix(mcp): guard discovery with cross-process lock 2026-07-28 14:31:24 -07:00
Atakan 56bda4529b fix(computer_use): revive ended cua-driver sessions once 2026-07-28 14:24:30 -07:00
atakan g 3d30232eba fix(delegate): isolate async batches from parent interrupts
Detached background delegation batches (_batch_runner) no longer honor
the foreground parent's interrupt flag — a busy-submit interrupt in the
TUI/desktop previously fabricated 'interrupted' results for background
children that should outlive the turn. Explicit cancellation still works
via _batch_interrupt.

Rebased onto current main from PR #65040; both interrupt-suppression
regression tests aligned with the current _session test helper.

Original work by @AtakanGs in #65040.
2026-07-28 14:20:10 -07:00
atakan g 7b18de5f40 fix: scope private URL policy per profile 2026-07-28 14:17:45 -07:00
William Reed 946ed96785 fix(voice): reconcile NeuTTS backbone/codec GPU device strings
llama_cpp's GGUF backbone loader only enables n_gpu_layers for the
literal device string "gpu"; torch's codec only accepts "cuda". A
single --device value passed straight through can't satisfy both,
so config.yaml's documented tts.neutts.device: cuda silently ran the
backbone on CPU while the codec ran on GPU.

Map cuda -> gpu for the backbone only; leave the codec on the
torch-native string. Measured 24.9s -> 13.1s per synthesis call on
an RTX 5070 Ti (neutts-air-q4-gguf) with this fix.
2026-07-28 14:07:21 -07:00
Que0x 555d4e10ad fix(tts): close temp WAV handle before playback in streaming fallback
`_play_via_tempfile` passes the NamedTemporaryFile *object* to `wave.open()`.
`wave.open()` flushes but does not close a file it did not open itself (by
name), so the OS handle to the temp WAV stays open. On Windows that open write
handle blocks the system player from reading the file and blocks the
`os.unlink()` cleanup (WinError 32, silently swallowed by `except OSError:
pass`), leaving orphaned temp .wav files piling up. The fallback runs whenever
no sounddevice output stream is available (sounddevice not installed / no audio
device), which is common on headless and Windows setups.

Close the temp file handle before invoking the player and again in the finally
block (idempotent), so the player can read the file and `os.unlink()` can
remove it.

Regression test drives `stream_tts_to_speaker` with the sounddevice path forced
unavailable and asserts the temp handle is closed before `play_audio_file` is
called (mutation-verified: reverting the close leaves the handle open at play
time and the test fails). Cross-platform.
2026-07-28 14:07:21 -07:00
3ASiC 45f7030786 fix(tts): bind MiniMax credentials to their region endpoint 2026-07-28 14:07:21 -07:00
Chaz Dinkle 7b0a575c82 fix(tts): use microsecond timestamp to prevent concurrent output path collision
Concurrent TTS requests within the same second (e.g. from voice prefetch)
generated identical tts_YYYYMMDD_HHMMSS.ogg paths, causing a race where
one request would unlink the file while another was still writing — resulting
in 'produced no output' errors.

Adding %f (microseconds) to the strftime format makes collisions practically
impossible. Registered as PATCH-006.
2026-07-28 14:07:21 -07:00
Vivaan Dhawan 1c30c57f11 fix(whatsapp): preserve voice notes when STT fails 2026-07-28 14:06:56 -07:00
Florian Valade 5277065260 feat(stt): add CAF format support with WAV conversion for cloud providers
Cloud STT APIs (Groq, OpenAI, etc.) cannot parse Apple CAF containers.
Add .caf to SUPPORTED_FORMATS and _convert_caf_to_wav() which tries
ffmpeg (cross-platform) then afconvert (macOS built-in).
2026-07-28 14:06:56 -07:00
Teknium 0cf58de85e
Merge remote-tracking branch 'origin/main' into wake-toggle-config
# Conflicts:
#	tests/test_tui_gateway_server.py
#	tui_gateway/server.py
2026-07-28 12:37:35 -07:00
Teknium e6b0344052 test: adapt salvaged voice tests to current main + lint fix
- _FakeProc gains returncode (main's player loop checks proc.returncode)
- WSL gate tests clear SSH_* env vars (main hard-warns over SSH without
  forwarded audio) and accept the merged #37346 forwarded-sound-server
  notice wording
- test_tts_macos_output stubs resolve_streaming_provider so the
  OutputStream setup path actually runs on main's chunked-streamer code
- voice CLI integration tests unwrap the _VoiceInputMessage sentinel
- _is_wsl: explicit encoding + drop unreachable return (ruff PLW1514)
2026-07-28 11:57:37 -07:00
Teknium fe3dc29009 fix(voice): honor quoted beep_enabled strings + correct PortAudio OSError hint
Two in-house micro-fixes from issue triage:

- #49883: voice.beep_enabled gates in cli.py and hermes_cli/voice.py used
  bool() on the config value, so a quoted YAML string like "false" or
  "off" kept beeps on. Route through utils.is_truthy_value.
- #18432: AudioRecorder.start() collapsed OSError from _import_audio into
  the 'pip install sounddevice numpy' hint — but OSError means the
  PortAudio SHARED LIBRARY is missing, which pip cannot fix. Mirror
  detect_audio_environment's system-package hint (libportaudio2 /
  brew portaudio / Termux pkg install portaudio) on that path.

Fixes #49883
Fixes #18432
2026-07-28 11:57:37 -07:00
RedClaus 1605cb5fe4 fix(voice): point pip install hint at venv pip instead of system Python
When Hermes runs inside its bundled venv (~/.hermes/profiles/<name>/
hermes-agent/venv/), the bare 'pip install sounddevice numpy' hint in
_voice_capture_install_hint() told users to install into whichever
Python their shell resolves first — on macOS that is often the system
Python under Rosetta, a completely separate site-packages tree with
incompatible wheel arches.

Detect venv via sys.prefix != sys.base_prefix and return the full path
to the venv's pip binary (Path(sys.prefix)/bin/pip) when available.
Falls back to the bare hint outside a venv (e.g. bare-metal installs).

Also adds 'from pathlib import Path' which was the only new import.
2026-07-28 11:57:37 -07:00
simonmmafs a1bc12f191 voice: one macOS output policy across WAV, beeps, streaming TTS + tests
Addresses review on #62601. Applies a single rule — no sounddevice for
audio OUTPUT on macOS (PortAudio/CoreAudio init triggers a
kTCCServiceMediaLibrary prompt) — consistently at all three output sites:

- play_audio_file: WAV playback (already routed to afplay) now uses the
  shared _sounddevice_output_allowed() helper.
- play_beep: synthesize the tone with numpy only, then on macOS play it
  via a temp WAV through afplay instead of sounddevice.
- stream_tts_to_speaker (tts_tool): on macOS, skip the sounddevice
  OutputStream so playback falls through to the existing tempfile/afplay path.

Audio INPUT (recording) is untouched — it legitimately needs mic permission.

Tests: TestMacOSAudioOutputPolicy (voice_mode) proves WAV + beep routing
does not import sounddevice on Darwin and still uses it off Darwin;
test_tts_macos_output proves streaming TTS skips the OutputStream on Darwin.
Existing test_play_wav_via_sounddevice pinned to non-Darwin for determinism.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 11:57:37 -07:00
Simon 0179ff9738 fix(voice): skip sounddevice on macOS to avoid TCC media-library prompt
On macOS, initializing PortAudio/CoreAudio via sounddevice triggers a
kTCCServiceMediaLibrary permission dialog even when no media-library
access is needed. afplay already handles WAV (and every other format)
natively, so route macOS playback straight to it and keep sounddevice
for other platforms.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-28 11:57:37 -07:00
xxxigm e3f4dc2103 fix(voice-mode): make Termux:API detection robust against pm probe failures
\`pm list packages com.termux.api\` is the canonical way to detect the
Termux:API Android app, but on some devices it gives a false negative
even when the app is installed and \`termux-microphone-record\` runs
fine — the symptom reported in #31015 (\`/voice on\` complaining
"Termux:API Android app is not installed").

Replace the single probe with a graded strategy:

1. Try \`pm list packages com.termux.api\` (current behaviour).
2. If \`pm\` isn't on PATH or returns non-zero, fall back to
   \`cmd package list packages com.termux.api\` — the modern Android
   API 28+ equivalent that's present on devices where \`pm\` is gone.
3. If both probes are inconclusive (binary missing, permission
   denied, timeout, or non-zero exit) and \`termux-microphone-record\`
   is on PATH, trust the binary.  The CLI ships in the \`termux-api\`
   package which is essentially only useful with the Android app
   installed; users who installed it deliberately almost always have
   the app too.

Polarity matters: a false negative on this gate blocks \`/voice on\`
entirely (the user-reported symptom), while a false positive only
surfaces a precise runtime error from the binary itself when it
tries to talk to the missing app — strictly more actionable.

The clean-probe-but-no-package case still returns False, so the
existing "Termux:API CLI installed without the app" warning still
fires when the package manager *can* tell us the app is missing.

Refs: NousResearch/hermes-agent#31015
2026-07-28 11:57:37 -07:00
ygd58 0560f52047 fix(voice): add WSL2 PowerShell audio fallback for TTS playback
Ports #63768 forward onto current main per teknium1's review.

On WSL2 without a PulseAudio bridge, ffplay and aplay have no audio
device and TTS playback silently fails (issue #17608). When
powershell.exe and ffmpeg are available, convert the audio to a
uniquely-named WAV in the Windows %TEMP% directory and play it via
Media.SoundPlayer.

Per review, this fixes two gaps in the original port:

1. Exit-status masking: the cleanup subshell was
   '( ffmpeg && powershell ); rm -f wav' -- the shell's exit status is
   the LAST command's (rm -f, which is always 0), so a real
   ffmpeg/PowerShell failure could never be detected by the rc-checking
   fallback logic added to the player loop. Now captures the real
   status before cleanup and re-exits with it:
   '( ffmpeg && powershell ); rc=0; rm -f wav; exit '.

2. The no-Pulse WSL gate in detect_audio_environment() still hard-blocked
   voice mode entirely (input AND output) even when the PowerShell
   fallback made TTS output viable. Added _wsl_powershell_tts_available()
   and use it to downgrade the WSL-without-Pulse case from a hard
   'warnings' block to a non-blocking 'notices' entry when the fallback
   is available -- the same PulseAudio-bridge recording guidance is still
   surfaced (mic capture genuinely still needs it), it just no longer
   blocks /voice on for TTS-only usage. cli.py's existing
   env_check['available'] gate needed no changes since it already
   respects this flag.

Also fixed the flaky uniqueness test (the original asserted
len(filenames) >= 2, which passed trivially on zero captured
filenames) and added a real fallback-triggering regression test for
the exit-status fix.

10 new/fixed tests pass in TestWSL2PowerShellFallback and the new
TestWSLAudioEnvironmentGate; 80/80 in the full tests/tools/test_voice_mode.py file.
2026-07-28 11:57:37 -07:00
Ivan Kharitonov ec7a46a6fe fix(voice): add WSL audio warmup to eliminate RDP crackling
WSLg RDP audio has two issues causing crackling:
1. systemd-timesyncd clock adjustments jitter PulseAudio timing
   (microsoft/wslg#1257) — user action: stop the service
2. Cold-start RDP connection drops first ~100ms of audio packets
   before the virtual channel stabilises

Fix (automated, WSL-only):
- Detect WSL via /proc/version 'microsoft' marker
- Prepend 100ms silence + apply 100ms fade-in to audio
- Append 50ms silence tail for clean stream teardown
- Set blocksize=4096 (default auto ~1024 is too small for RDP)
- All in a single continuous sd.play() buffer

Non-WSL paths unchanged.

Closes #38893
2026-07-28 11:57:37 -07:00
Slippy87 ef686c3878 fix(voice): honor forwarded audio (PIPEWIRE_REMOTE) in WSL detection 2026-07-28 11:57:37 -07:00
Brice 2a75664c0c fix(voice): capture at the input device's native sample rate
AudioRecorder hard-codes SAMPLE_RATE (16 kHz) when opening the input
stream, but some capture devices (e.g. USB microphones exposed through
ALSA hw) reject 16 kHz outright — sd.InputStream fails with
PaErrorCode -9997 (Invalid sample rate) and voice recording is broken.

Query the default input device for its native default_samplerate at
recording start and open the stream / write the WAV at that rate,
falling back to the Whisper-friendly 16 kHz constant when the backend
does not expose a usable rate. STT providers accept standard WAV rates,
so downstream transcription is unaffected.
2026-07-28 11:57:37 -07:00
Kewe63 f98952b267 feat(voice): make beep notification volume configurable from config.yaml
Closes #55908. The CLI voice-mode beep amplitude is hardcoded at 0.3 inside
tools.voice_mode:play_beep(), which makes the record start/stop cues too
quiet on low-volume systems and headphones. Users couldn't adjust it
without editing source.

Move the literal into a configurable voice.beep_volume setting (clamped to
0.0-1.0, default 0.3 to preserve prior behaviour). The new
_get_beep_volume() helper reads via the same load_config() pattern used by
cli.py's _voice_beeps_enabled() and hermes_cli/voice.py's _beeps_enabled(),
keeps bools / out-of-range / non-numeric / NaN values safely on the default,
and falls back silently if config can't load so the audio cue never breaks
the voice loop on a degenerate config.yaml.

Covered by tests/tools/test_voice_mode.py:
- TestGetBeepVolume (12 cases: missing key, custom value, boundary 0.0/1.0,
  out-of-range clamp, type coercion, bool guard, NaN guard, exception
  guard, dict-typed voice section)
- TestPlayBeepVolumeWiring (guards against re-introducing a hardcoded 0.3
  literal in play_beep)

Docs: website/docs/user-guide/configuration.md mentions the new key.
Other locale translations (zh-Hans etc.) intentionally untouched —
handled by the regular i18n sync pipeline as a separate change.

No change in default behaviour: existing users hear exactly the same beep.
2026-07-28 11:57:37 -07:00
Solitud1nem fd213a82f4 fix(voice): enforce voice.max_recording_seconds (was dead config) 2026-07-28 11:57:37 -07:00
shellybotmoyer 88f7fe3b1f fix(tts): improve Opus encoding quality for voice messages
Salvaged from PR #18861 (@shellybotmoyer). Switch the central Opus
transcoders from CBR 64k (-vbr off) to VBR 48k with -application voip and
-compression_level 10. The old CBR settings produced lower-quality speech
audio and occasionally failed to trigger Telegram's native voice-bubble
rendering. Applied to _ffmpeg_transcode_to_opus (the single transcoder
behind _convert_to_opus and _repair_ogg_container), the Gemini WAV→OGG
path, and the Matrix adapter boundary transcoder added in this branch.

Fixes #18818
2026-07-28 11:55:48 -07:00
Teknium 4aac89b429 fix(tts): unify TTS text preprocessing behind one shared cleaner
Consolidates all TTS text-preparation paths onto
tools/tts_text_normalize.prepare_spoken_text:

- strip_nonspoken_blocks: removes <think> reasoning blocks (#34213,
  incl. unterminated streaming blocks) and the end-of-turn
  file-mutation verifier footer emitted by run_agent.py (#40772).
- flatten_newlines_for_payload: collapses newlines into sentence
  breaks so newline-sensitive OpenAI-compatible providers (Kokoro)
  speak the whole script instead of truncating at the first newline
  (#9004).
- tools/tts_tool._strip_markdown_for_tts (voice-mode streaming + web
  dashboard path) now delegates to the shared cleaner, with the legacy
  regex pipeline kept as a best-effort fallback.
- hermes_cli/voice.py speak_text and cli.py _voice_speak_response now
  use the shared cleaner instead of their own duplicated regex
  pipelines.
- gateway auto-TTS fallback also strips think blocks.

Tests: tests/tools/test_tts_prepare_spoken.py covers think blocks,
verifier footer, emoji, newline flattening, and the shared-cleaner
wiring on the tool/streaming/gateway paths. Updated the header
expectation in test_voice_cli_integration.py for the heading-fold
behavior of the shared cleaner.

Closes #34213, #9004, #40772
2026-07-28 11:55:01 -07:00
Gabriel Anzziani c0dda61032 feat(tts): pass lang_code to OpenAI-compatible TTS providers (Kokoro multilingual support)
The 'language' config field in tts.openai.language was read but never passed
to the API. This caused Kokoro (and other OpenAI-compatible TTS backends that
support lang_code) to default to English phonemization regardless of the
configured language.

Now passes lang_code via extra_body when language is set in config.
2026-07-28 11:55:01 -07:00
Carlos Diosdado d1e9344716 feat(xai-tts): wire text_normalization parameter
xAI TTS supports a text_normalization boolean that normalizes
written-form text (numbers, abbreviations, symbols) into spoken-form
before synthesis. This parameter was not being sent, leaving users
with literal number/symbol pronunciation.

- Add DEFAULT_XAI_TEXT_NORMALIZATION_DEFAULT = False
- Read tts.xai.text_normalization from config (via _xai_bool_config)
- Attach text_normalization: true to the POST payload when enabled
- Omit the field entirely when unset or explicitly false (API default)
- Add 3 tests: default omission, enabled passthrough, explicit false
2026-07-28 11:55:01 -07:00
Carlos Diosdado 462b3cf994 feat(tts): add optional provider parameter to text_to_speech tool
Adds an optional provider parameter to the text_to_speech tool that lets the model select a TTS provider per-call instead of always using the globally configured tts.provider.

When provider is set, it bypasses the configured default and routes directly to the specified backend.

When omitted (the default), the tool behaves exactly as before.

Closes #47459
2026-07-28 11:55:01 -07:00
Alcibiades Athens 1daa76951b feat(tools): forward OpenAI TTS instructions field through text_to_speech
The `text_to_speech` tool schema accepted only `text` and `output_path`,
so style direction (tone, emotion, pacing, whispering) could never reach
the OpenAI backend — even though `gpt-4o-mini-tts` (Hermes's OpenAI
provider default) treats `instructions` as its primary voice-design
control.

This plumbs an optional `instructions` argument through the tool schema,
the handler lambda, and `text_to_speech_tool()` into
`_generate_openai_tts`, where it is forwarded to
`client.audio.speech.create()` only when truthy. Empty/None values still
omit the key entirely, preserving behavior on `tts-1`/`tts-1-hd` and
strict OpenAI-compatible servers.

The same passthrough unblocks self-hosted OpenAI-compatible voice-design
servers (Qwen3-TTS-VoiceDesign on oMLX, etc.) that are already wired in
via `tts.openai.base_url` — the established convention per #9004 and the
TTS config docs — without inventing a new provider backend.

Tests: `tests/tools/test_tts_instructions.py` covers backend passthrough,
tool-level threading, schema declaration, and the empty-string/absent
omission cases. `tests/tools/test_tts_max_text_length.py` fake_openai
signature widened to accept the new kwarg.

Refs NousResearch/hermes-agent#14196
2026-07-28 11:55:01 -07:00
Hu 8171e8ebb3 feat(tts): expose speed parameter in text_to_speech tool
Add optional 'speed' parameter (0.25-4.0) to the text_to_speech tool
schema and handler. When provided by the model, it overrides the
config-level tts.speed setting, enabling per-request speed control
without config changes.

Use cases:
- Language learning: slow playback (0.5x) for pronunciation practice
- Accessibility: adjustable speed for hearing preferences
- Content review: accelerated playback for long text

The speed value is clamped to [0.25, 4.0] and injected into tts_config
before dispatching to any provider (Edge, OpenAI, MiniMax, etc.), so
all existing provider-level speed handling works transparently.

Includes 3 new tests for tool-level speed injection, clamping, and
config preservation when speed is not specified.
2026-07-28 11:55:01 -07:00
Johann d9336e7453 fix(tts): strip <think> reasoning blocks from TTS text
When /reasoning show is enabled, the model's <think> blocks appear in
the final assistant message. TTS reads these aloud, which is unwanted —
users want to see reasoning but not hear it spoken.

- Add _THINK_BLOCK regex to _strip_markdown_for_tts() (tools/tts_tool.py)
  — the general TTS text-preparation path used by all TTS providers
- Add <think> stripping to prepare_tts_text() (gateway/platforms/base.py)
  — the gateway auto-TTS path
- Reuses the existing regex pattern from stream_tts_to_speaker()

Closes #34213
2026-07-28 11:55:01 -07:00
Alexander Russell a9a9005f31 feat(tts): normalize spoken text (units, symbols, markdown) before synthesis
Auto-TTS previously fed raw chat Markdown and compact symbols straight to the
speech provider, so units were read as stray letters and headings or bullets ran
together. This routes spoken text through a new normalizer,
tools/tts_text_normalize.prepare_spoken_text, that expands units (for example a
temperature written with the degree symbol becomes "degrees Celsius") and
flattens Markdown into a transcript-like script with sentence pauses.

The normalizer is best-effort: if it ever fails the code falls back to the
previous markdown-strip behavior, so auto-TTS keeps working. The Telegram voice
caption uses the same normalized text. Includes a unit test.
2026-07-28 11:55:01 -07:00
Tikkanaditya Siddartha Jyothi 90b68520ac fix(tts): bound the Piper/KittenTTS model caches with a small LRU
Salvaged from PR #62977 (@Vissirexa) — TTS model-cache half only (the
hindsight turn-buffer half is a different subsystem and was dropped).

_piper_voice_cache and _kittentts_model_cache were keyed by voice/model
with no eviction, and each entry is a whole loaded model (tens of MB).
A surface that sweeps voices pinned one model per voice for the process
lifetime. New _tts_cache_get_or_load() get-or-loads through a small LRU
(_TTS_MODEL_CACHE_MAX=3), refreshing recency on a hit and evicting the
least-recently-used model on a cold miss.
2026-07-28 11:54:26 -07:00
luyifan 60b841bbfb fix(tts): bound upstream response bodies 2026-07-28 11:54:26 -07:00
Teknium 43b8eb84b3 fix(tts): base_url parity audit — Mistral server_url + provider config tests
Class-level sweep following the ElevenLabs salvage (#66311): every cloud
TTS provider section now honors tts.<provider>.base_url. xAI, MiniMax,
Gemini, OpenAI and DeepInfra already did; Mistral (SDK server_url) was
the remaining gap. Adds per-provider config tests locking in the
ElevenLabs environment plumbing and the Mistral server_url passthrough.
2026-07-28 11:54:26 -07:00
Moeadham e5fc806ccc fix(tts): support configurable ElevenLabs URLs
Salvaged from PR #66311 (@moeadham), rebased onto the current streaming
registry. tts.elevenlabs.base_url (+ optional wss_url, derived from
base_url when omitted) routes both the sync ElevenLabs path and the
chunked ElevenLabsStreamer through an ElevenLabsEnvironment, matching
the STT side's ELEVENLABS_STT_BASE_URL/config override pattern.
2026-07-28 11:54:26 -07:00
Teknium 3356703d1f fix(tts): streaming path also honors tts.openai.api_key from config
Follow-up to salvaged PR #70307 (@aml1973): OpenAIStreamer now checks
tts.openai.api_key (config.yaml) ahead of the env resolver in both
available() and stream(), completing config parity between the sync
and streaming OpenAI TTS paths.
2026-07-28 11:54:26 -07:00
aml1973 861c2fecd2 fix(tts): honor OpenAI config for streaming
Use the shared OpenAI audio key resolver and prefer tts.openai.base_url over the global environment fallback in the Desktop streaming path. Add focused regression coverage for credential and endpoint propagation.
2026-07-28 11:54:26 -07:00
LeonSGP43 efc81a19a6 fix(tts): honor tts.openai.api_key and base_url from config.yaml
Salvaged from PR #26233 (@LeonSGP43), rebased onto the current 3-tuple
_resolve_openai_audio_client_config (is_managed flag, post-#73072 layout).
Same fix independently submitted earlier in PR #26209 (@zccyman) — credit
to both.

Resolution order now mirrors the STT resolver: tts.openai.api_key/base_url
from config.yaml -> VOICE_TOOLS_OPENAI_KEY/OPENAI_API_KEY env (still
honoring config base_url) -> managed gateway. _has_openai_audio_backend
also counts a config api_key as an available backend.

Fixes #26175
2026-07-28 11:54:26 -07:00
dsad f96eee3a91 fix(xai): pin oauth side-tool base URLs 2026-07-28 11:54:01 -07:00
Ben Sheridan-Edwards bcbae3bf41 fix(stt): cover 401 retry and keep proof image out of the merge diff
- parametrize the OAuth retry regression over HTTP 401 and 403 so both
  documented rejection statuses are exercised
- reword the retry-failure warning: the except block also covers the
  retried request, not just the credential refresh
- drop docs/proof/ from the PR diff; the live-proof screenshot now lives
  on the fork's proof-assets-xai-stt-oauth-retry branch and stays linked
  from the PR description
2026-07-28 11:54:01 -07:00
BenSheridanEdwards 36de3c5c3e fix(stt): retry xAI OAuth after auth rejection 2026-07-28 11:54:01 -07:00
Tobias Safaie geb. Schmidt-Philipp d889c980f5 fix(stt): prefer explicit xAI API key 2026-07-28 11:54:01 -07:00
Teknium c0c5dac531 fix: stdin=DEVNULL + windows_hide_flags on STT transcode subprocess (guard test) 2026-07-28 11:53:36 -07:00
Teknium d66ec2f5f4 fix: explicit utf-8 encoding on ffmpeg STT transcode subprocess (Windows footgun lint) 2026-07-28 11:53:36 -07:00
Teknium 0897e0adb8 test: align dispatch tests with provider-scoped validation and named registration errors
Follow-ups for the salvaged wave: the auto-detect legacy-error test now
stubs the split validators, the unknown-command-provider test expects
the new provider_not_registered error, and _transcribe_local tolerates
a null stt.local config section again.
2026-07-28 11:53:36 -07:00
Teknium 9467dc135f fix(stt): lock local model load; allow keyless local OpenAI-compatible STT
Two small fresh fixes on top of the salvage wave:

- Wrap the check-then-load of the module-global faster-whisper model in a
  double-checked threading.Lock so concurrent voice messages can't both
  download/load the model (#24767).
- Treat an empty stt.openai.api_key as no-auth when stt.openai.base_url
  points at a loopback/RFC-1918/.local host, so local OpenAI-compatible
  STT servers (faster-whisper-server, speaches, vLLM whisper) work
  without a sham api_key value. Reimplements the idea from PR #25193 —
  credit @nnnet.

Co-authored-by: nnnet <nnnet@users.noreply.github.com>
2026-07-28 11:53:36 -07:00
Carl Borg ef0d8ce2c5 transcription: transcode to m4a and retry when OpenAI STT rejects the audio container
Newer OpenAI transcription models (gpt-4o-transcribe, gpt-4o-mini-transcribe)
reject some containers the legacy whisper-1 endpoint accepted -- notably the
Ogg/Opus voice notes messaging platforms deliver -- returning a 400
'corrupted or unsupported' error, so voice-note transcription fails for users
on those models even though SUPPORTED_FORMATS still advertises .ogg/.aac/.flac.

Wrap the OpenAI upload: on a format-related BadRequestError, transcode the
source to a compact 16 kHz mono AAC .m4a via ffmpeg and retry once. This is
model-agnostic (no per-model format table to maintain) and adds no cost for
formats the endpoint already accepts.

Fixes #68719
2026-07-28 11:53:36 -07:00
Dennis f50a7c307a fix(stt): preprocess .silk voice notes before transcription
Decode WeChat/QQ SILK v3 voice notes to WAV inside transcribe_audio so
any platform that caches a .silk file gets STT for free (same central-
normalization philosophy as the outbound container repair). pilk is
lazy-installed on first use (stt.silk in tools/lazy_deps.py) instead of
being added to the voice extra.

Fixes the inbound half of #32196.

(cherry picked from commit e5db79369d; reworked to compose with the
provider-scoped upload size cap and to lazy-dep pilk)
2026-07-28 11:53:36 -07:00
Damian Kluk a784e74c7f fix(stt): better error logging when faster-whisper lazy install fails
Log lazy-install failures at WARNING instead of DEBUG, with actionable
guidance about venv write-permission issues (the most common cause of
silent STT failures).

Salvaged from PR #46127 (transcription_tools half only — the gateway DM
hunks are superseded by main's neutral-marker enrichment design, and the
Docker/CI files were unrelated scope).

(cherry picked from commit d3e07bdaaa, reduced)
2026-07-28 11:53:36 -07:00
Zehua Wang 7a56ab2aa2 fix(stt): validate selected voice provider availability 2026-07-28 11:53:36 -07:00
Zehua Wang eaa2dd6d09 fix(stt): check selected provider (not any) + plugin support
PR review feedback:
- Replace _has_any_command_stt_provider() with selected-provider
  check via _resolve_command_stt_provider_config()
- Add _check_plugin_stt_provider() for plugin-registered backends
- Add tests: selected command, unrelated command (should NOT pass),
  and plugin provider path
2026-07-28 11:53:36 -07:00
Zehua Wang de057fe24f fix(stt): check_voice_requirements() should recognize all STT providers
The /voice status command only checked for 'local', 'groq', and 'openai'
providers. Any other valid provider (local_command, mistral, xai,
elevenlabs, or custom command providers) fell through to the generic
MISSING message — even when transcription worked perfectly.

- Import _has_any_command_stt_provider (already defined, never imported)
- Add elif branches for local_command, mistral, xai, elevenlabs
- Add generic catch-all via _has_any_command_stt_provider() for
  arbitrary custom command providers
2026-07-28 11:53:36 -07:00
LauraGPT 7d2b8a3cad fix(stt): anchor qwen asr envelope stripping 2026-07-28 11:53:36 -07:00
LauraGPT d219392e5b fix(stt): anchor Qwen3-ASR envelope stripping 2026-07-28 11:53:36 -07:00
LauraGPT 517b8debbd fix(stt): strip Qwen3-ASR response prefix
Normalize the structured <asr_text> marker after extracting text from string, SDK object, and dictionary transcription responses. Preserve the current provider-aware STT configuration architecture.

Refreshes #8773 on current main.

Co-authored-by: angelos <angelos@oikos.lan.home.malaiwah.com>

Assisted-by: Codex:gpt-5.6
2026-07-28 11:53:36 -07:00
luyifan a5074c0ca8 fix(stt): report unregistered configured providers 2026-07-28 11:53:36 -07:00
Tushar a6a439338e fix(tts): fall through to raw import when lazy_deps fails (#53259)
Replace 
aise ImportError(str(e)) with pass in the except Exception
handler of _import_edge_tts(), _import_elevenlabs(), and
_import_mistral_client() so packages installed via PYTHONPATH or Docker
layered filesystems still work when lazy_deps.ensure() raises.

Also fix the Mistral STT path in transcription_tools.py which only
caught ImportError, not FeatureUnavailable.

Adds 6 regression tests using sys.modules fixtures (no
builtins.__import__ patching).
2026-07-28 11:53:36 -07:00
Charles Cha ffc3ce27d5 fix(stt): scope upload size limits to remote providers 2026-07-28 11:53:36 -07:00
AnthonyAssistantAi 884900ffd6 fix: avoid local STT crash on Apple Silicon
Force CPU (int8) for faster-whisper on Apple Silicon / Rosetta, where
ctranslate2's device=auto path can hard-abort in native code. Salvaged
from PR #28624 without the numpy pin change (main already moved on).

(cherry picked from commit 7edf2d5196, pyproject.toml hunk dropped)
2026-07-28 11:53:36 -07:00
liuhao1024 766e856118 fix(stt): treat CUBLAS_STATUS_NOT_SUPPORTED as CUDA lib error
- Add Blackwell-specific cuBLAS error marker to _CUDA_LIB_ERROR_MARKERS
- Allows CPU fallback on RTX 5090 (sm_120) when faster-whisper
  reports CUBLAS_STATUS_NOT_SUPPORTED instead of loading successfully
- Add regression test for CUBLAS_STATUS_NOT_SUPPORTED path

Closes #17526
2026-07-28 11:53:36 -07:00
Tranquil-Flow 06fc6e0c29 fix(stt): respect device and compute_type from config.yaml
The local STT transcription function hardcoded device="auto" and
compute_type="auto" when instantiating WhisperModel, ignoring the
user's stt.local.device and stt.local.compute_type config values.

Closes #8319
2026-07-28 11:53:36 -07:00
Teknium c136400c9e fix(voice): single scoped resolver — STT/TTS keys fall back to the credential pool
Rework of #68509 per triage: hoist the duplicated per-tool
_resolve_provider_key helpers into one owner,
tools.tool_backend_helpers.resolve_provider_secret(), and migrate every
STT/TTS key lookup site to it.

Resolution order: explicit config.yaml value > profile secret scope /
env / ~/.hermes/.env > credential pool (checks both '<provider>' and
'custom:<provider>' pool keys, so keys added via 'hermes auth add
mistral' or declared under providers.<name> both resolve). Under an
active multiplex turn the profile scope stays authoritative — no pool
or .env fallback that could borrow another profile's key (composes with
the #69469 scope fix).

Coverage now includes GROQ_API_KEY, MISTRAL_API_KEY, ELEVENLABS_API_KEY,
DEEPINFRA_API_KEY, MINIMAX_API_KEY, GEMINI_API_KEY/GOOGLE_API_KEY, the
XAI_API_KEY fallback in resolve_xai_http_credentials, and the OpenAI
audio key (resolve_openai_audio_api_key now pool-aware for
OPENAI_API_KEY via 'hermes auth add openai-api').

Unit tests: fake pool entry proves each provider resolves from the pool
when env is empty; env still wins when set; config wins over both; a
multiplex scope miss never borrows the pool; pool read failures never
raise; tool-level wiring for STT, TTS, xAI, and OpenAI audio.

Fixes #68003
2026-07-28 11:53:09 -07:00
sg-architect 79bcfc23ab fix(tools): resolve TTS/STT provider keys through credential pool
TTS/STT providers (Mistral, ElevenLabs) only checked env vars and
.env files via get_env_value(), ignoring keys stored via
'hermes auth add mistral' / 'hermes auth add elevenlabs'.

Add _resolve_provider_key() helper that falls back to the credential
pool (agent.credential_pool.load_pool) when the env var is unset.

Affected:
- tools/transcription_tools.py: 6 sites (provider selection + auto-detect)
- tools/tts_tool.py: 6 sites (synthesis + availability check)

Fixes #68003
2026-07-28 11:53:09 -07:00
Drexuxux ed591a5664 fix(voice): resolve the TTS/STT OpenAI key under the profile secret scope
`resolve_openai_audio_api_key()` reads the key that authenticates the audio
client straight from the process environment:

    return (
        os.getenv("VOICE_TOOLS_OPENAI_KEY", "")
        or os.getenv("OPENAI_API_KEY", "")
    ).strip()

That value is not advisory. It flows through
`_resolve_openai_audio_client_config()` into `OpenAIClient(api_key=...)` for
TTS, and through `transcription_tools` for voice-note STT — both on the
per-turn tool path, inside the profile secret scope the gateway installs.

`agent/vertex_adapter` states the contract this breaks:

    in a multiplex gateway serving several profiles from one process,
    os.environ reflects whichever profile's .env happened to be loaded at
    boot, not the profile the current turn belongs to. Reading it directly
    here would let one profile mint tokens from — and get billed against —
    a different profile's service-account file.

Reproduced with the real resolver, multiplexing on and profile A's scope
installed:

    scope-aware get_secret  -> sk-PROFILE-A-key
    voice/STT resolver      -> sk-PROFILE-B-key

So profile A's spoken reply and its users' voice notes are sent to OpenAI on
profile B's account, and billed there.

Route both reads through `agent.secret_scope.get_secret`, the same fix already
merged for the WeChat send path (#59662) and pending for QQ (#60420) — neither
covers the audio credential family. Under multiplexing the scope stays
authoritative, so a scope miss now yields no key instead of borrowing another
profile's; with multiplexing off `get_secret` falls through to `os.environ`
exactly as before, so single-profile deployments are untouched. The
VOICE_TOOLS_OPENAI_KEY > OPENAI_API_KEY precedence is unchanged.

Deliberately narrow: `fal_key_is_configured()` and
`has_direct_modal_credentials()` in this file are presence checks, not
authentication, and the former is already being reworked in open PR #20929.

tests/tools/test_tool_backend_helpers.py: the scope wins over another
profile's `os.environ`; a scope miss does not borrow another profile's key;
voice-key precedence holds inside a scope; and a control proves the
single-profile path still reads `os.environ`. The three isolation tests fail
on main; the control passes there. 320 passed across the helper, secret-scope,
and consumer suites (the fluctuating voice_mode/voice_cli failures are
pre-existing PulseAudio/ordering artifacts — the differing test passes 3/3 in
isolation on both main and this branch).
2026-07-28 11:53:09 -07:00
Teknium d464ae3652 feat(cron): user-owned model pins + cron.model fleet default
Per-job cron inference pins are now user-owned: the agent-facing cronjob
tool schema no longer exposes model/provider/base_url, and the registered
handler ignores them even if a model hallucinates the old parameters.
Users set pins via the dashboard, hermes cron create/edit --model/--provider,
or jobs.json directly — and once set, a pin sticks until the user changes it.
Existing agent-era pins are grandfathered untouched.

New cron.model / cron.model_provider config keys give the cron fleet its
own default model, independent of the chat model. Fire-time resolution:
per-job pin > cron.model > HERMES_MODEL > model.default. An axis covered
by the explicit cron-fleet default is deliberate routing, not drift, so
the #44585 fail-closed guard skips it — switching your chat model with
/model or hermes model no longer breaks unpinned cron fleets.

- tools/cronjob_tools.py: drop model param from agent schema + handler;
  remove now-dead _resolve_model_override
- cron/scheduler.py: cron.model/model_provider resolution + per-axis
  drift-guard skip
- cron/jobs.py: snapshot resolution mirrors the new precedence
- hermes_cli/subcommands/cron.py + hermes_cli/cron.py: --model/--provider
  on hermes cron create/edit
- hermes_cli/config.py: cron.model / cron.model_provider defaults
- docs: cron.md model-resolution tip rewritten
2026-07-28 11:52:47 -07:00
Teknium 156edc5ded refactor: extract shared audio container sniffer to tools/audio_container.py
One sniffer owns magic-byte container detection (Teknium's one-concept-
one-owner rule): the new tools/audio_container.py is used by

- gateway/platforms/base.py _sniff_audio_ext (inbound cache — PR #36166's
  central sniffer, now covering AAC/ADTS, MP4-brand disambiguation, webm)
- gateway/platforms/signal.py _guess_extension (audio/AV branches
  delegated; RIFF/WAVE fix from PR #50690 and M4A-brand fix from
  PR #72490 now live centrally)
- tools/tts_tool.py _sniff_audio_container (outbound repair, PR #73072)

cache_audio_from_url inherits the sniff via cache_audio_from_bytes.
Adds tests/tools/test_audio_container.py covering every magic-byte type,
wrong-extension repair on the inbound cache, unknown passthrough, the
URL path, and Signal's delegation.
2026-07-28 11:52:44 -07:00
luyifan 4ae27548d6 fix(media): recognize m2a audio attachments 2026-07-28 11:52:44 -07:00
Elie BRUNO 971cb9b886 fix(stt): accept .oga and .opus voice notes for transcription
Telegram sends voice notes as .oga (OGG/Opus). SUPPORTED_FORMATS listed
.ogg but not .oga, so transcribe_audio rejected every Telegram voice note
with "Unsupported format: .oga" before reaching any STT backend. Add .oga
and .opus to the allowlist, with a regression test.
2026-07-28 11:52:44 -07:00
Teknium f106e0ebc2
fix(wake): raise default sensitivity to 0.6 and fix inverted Porcupine direction
'hey hor' triggered the wake word: the default sensitivity was 0.5, which
for openWakeWord IS the raw per-frame score threshold — openWakeWord's own
permissive baseline that near-misses clear. Raised the default to 0.6 so
phonetic near-misses fall short while real 'hey hermes' (typically 0.9+)
still fires easily.

Also fixed a real cross-engine inconsistency found while checking: the
sensitivity knob is documented 'higher = stricter' and behaves that way
for openWakeWord (threshold = sensitivity) and sherpa (0.05 + 0.4*s), but
Porcupine's own 'sensitivities' param runs the opposite way (higher = MORE
false alarms, per Picovoice). Turning sensitivity up made Porcupine looser
— backwards. Now inverted (1 - sensitivity) so 'higher = stricter' holds
for every engine.

- tools/wake_word.py: default 0.6; _sensitivity fallback uses _DEFAULTS;
  Porcupine sensitivity inverted with rationale
- hermes_cli/config.py + docs: default + consistent-direction note
- tests: Porcupine inversion, default>=0.6 regression, fallback-to-default
2026-07-28 09:43:17 -07:00
Alex Fournier b1a5d67e71 Merge upstream main into fix/hermes-relay-anthropic-context
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-28 08:10:58 -07:00
Teknium 30ed3f82bd
fix(wake): reject ambient-speech false triggers with consecutive-frame confirmation
openWakeWord scores one ~80ms frame at a time and the detector fired the
instant a SINGLE frame crossed threshold — so a stray phoneme in background
conversation could trigger the wake word unintentionally (reported in
testing). A real utterance of the phrase holds a high score across several
consecutive frames; an ambient blip spikes just one.

_OpenWakeWordEngine now requires N consecutive over-threshold frames
(wake_word.confirmation_frames, default 3) before firing. The streak resets
on any sub-threshold frame and on engine reset() (pause/resume), so a
pre-pause frame can't count toward a post-resume fire. confirmation_frames=1
restores the old single-frame behavior; clamped 1..10.

Only openWakeWord is affected — sherpa (streaming transducer) and porcupine
decode the whole phrase internally and already reject single-frame spikes.

- tools/wake_word.py: _confirmation_frames() accessor, streak logic in
  process()/reset(), config default
- hermes_cli/config.py: wake_word.confirmation_frames documented default
- tests: 5 new (spike rejected, sustained fires once, =1 legacy behavior,
  reset clears streak, config clamp) — 58 wake tests green
- docs: 'Reducing false triggers on ambient speech' section
2026-07-28 07:59:35 -07:00
Ben Barclay 7d19033d2e
fix(wake): run openWakeWord on tflite on macOS ARM64
openWakeWord's ONNX backend returns near-zero scores on Apple Silicon
(dscripka/openWakeWord#336), so "Hey Hermes" never crossed the 0.5
threshold: the listener armed, the microphone worked, and nothing fired.

Bisecting the pipeline puts the fault in exactly one stage — feeding the
same audio through both backends, the melspectrogram front-end is
bit-identical (maxdiff 0.00000) and the wake classifier agrees on
identical features, while the shared embedding model diverges by 45.44.
Cross-feeding confirms it: tflite features scored through the *onnx*
classifier give 0.9948 vs 0.000009 for onnx features. A telling
secondary symptom is that scores fall as input gets louder (0.5x ->
0.00031, 8x -> 0.000066), which is garbage inference rather than a weak
detection.

Selecting tflite in config alone does not fix it. openWakeWord hardcodes
`import tflite_runtime.interpreter` but declares tflite-runtime for
`platform_system == "Linux"` only; on macOS the equivalent wheel is
ai-edge-litert, so that import always fails and model.py silently
downgrades back to onnx. The result is a detector that reports itself
listening and can never fire.

- default the backend per platform (tflite on macOS ARM64, onnx
  elsewhere) instead of hardcoding onnx, and pick the matching bundled
  model artifact
- bridge tflite_runtime -> ai_edge_litert through sys.modules, in-process,
  with no writes to site-packages
- refuse the silent onnx downgrade on macOS ARM64 and report the missing
  runtime through check_wake_word_requirements() so the GUI surfaces an
  actionable hint rather than arming a dead ear
- lazy-install ai-edge-litert via its own feature key, because lazy-dep
  specs cannot carry PEP 508 markers (_spec_is_safe rejects ";")

An explicit `inference_framework` in config still wins, so anyone pinning
a backend keeps it.

Verified on macOS 26.5.2 / M-series: "hey hermes" scores 0.0005 on onnx
and 0.9423 on tflite from the same clip, with cross-phrase controls at
0.0003. Live over-the-air through the real microphone fires 4/4
utterances (peak 0.9532).
2026-07-28 07:59:34 -07:00
Teknium a832139ba3
feat(wake): eager-install voice deps with the desktop; wake probes never run pip
Two fixes from live testing (Teknium):

1. Desktop installs now ship the wake/voice stacks up front.
   install.sh + install.ps1 desktop stages run 'uv pip install
   -e .[wake,voice]' (best-effort, lazy-install remains the fallback)
   before building the app, so the first ear-click arms instantly
   instead of sitting through a multi-minute onnxruntime download.
   CLI-only installs keep the lazy path — [all] curation unchanged.

2. The vanished ear: the STT/TTS gate made wake.status call
   check_tts_requirements(), whose edge path runs _import_edge_tts →
   lazy_deps.ensure — a synchronous PIP INSTALL inside a status poll.
   On a venv without edge-tts that blew the desktop's 30s RPC timeout,
   armWakeWord caught the error, the atom never learned enabled=true,
   and the ear unmounted. _tts_ready is now a pure probe: deps missing
   + lazy installs allowed counts as ready (installs at first speak)
   WITHOUT touching pip; check_tts_requirements only runs once deps
   are present. Regression test asserts the probe never calls it while
   deps are missing.
2026-07-28 07:59:34 -07:00
Teknium f03bb2b4ef
feat(wake): gate arming on STT + TTS readiness
The wake loop is wake → record → STT → agent → TTS. Arming without
either end configured gives a mic that hears you and then does nothing
perceivable — a useless experience. check_wake_word_requirements now
probes both (same probes /voice uses: stt.enabled + provider != none;
check_tts_requirements) and refuses with a pointer to `hermes tools`
naming exactly which half is missing. The desktop ear hides (available:
false already hides the button), /wake on prints the hint on CLI/TUI.

wake.start also validates requirements BEFORE persisting
wake_word.enabled, so a refused gesture can't leave config claiming on
while nothing can ever arm.

Tests: per-half and both-missing hint assertions; existing requirements
tests pinned via _voice_loop_ready so they don't depend on the test
venv's installed voice stack. E2E: stt.enabled=false in a real config
-> unavailable with the speech-to-text hint.
2026-07-28 07:59:34 -07:00
Teknium 514dd59cad
fix(wake): detect dead-mic streams, stop the ear freezing during first-use install
Internal testing (macOS): clicking the ear froze the button for ~30s,
then it went blue but 'hey hermes' never fired even though STT worked.

Two distinct bugs:

1. Frozen-then-timeout button: first-use wake.start lazy-installs the
   detection engine (onnxruntime is a large wheel), which blows the
   desktop's default 30s WS request timeout — the RPC 'failed' client-
   side while the backend kept installing and armed later on its own.
   wake.start now gets a 180s budget and the pending state says
   'arming — first use may take a minute while the engine installs'
   instead of a silent disabled button.

2. Armed but deaf: macOS grants mic permission per PROCESS. The
   renderer having mic access (STT working) does not grant the Python
   backend anything — CoreAudio hands an unentitled process a 'working'
   stream that delivers zeros forever, so the listener looks healthy
   and can never hear the phrase. The detector now tracks frame peaks:
   10s of consecutive near-zero frames sets audio_silent, logged with
   the exact macOS Settings path, cleared automatically when audio
   appears. Surfaced everywhere: wake.status (audio_silent + hint),
   desktop ear tooltip (kept visible while listening), /wake status on
   TUI (⚠ line) and classic CLI, plus a docs troubleshooting section.

Tests: detector silent-flag set/recover cycle (fake silent/loud
streams), desktop tooltip keeps the dead-mic hint while listening.
44 wake Python tests, 22 desktop + 14 TUI vitest green.
2026-07-28 07:59:34 -07:00
Teknium 7a87c6ffd6
fix(wake): make the lazy-install path reachable on fresh installs
check_wake_word_requirements() gated 'available' on the audio probe,
but the probe imports sounddevice + numpy — two of the packages the
lazy installer would install. On a fresh machine deps_ok was False, so
audio_ok was always False and /wake on printed the manual pip hint and
bailed before the engine constructors' lazy_deps.ensure() could run.

Now the audio probe only runs once deps are installed; with deps
missing and lazy installs allowed (the default), /wake on proceeds and
ensure() installs the pinned engine deps in-process — no restart. The
manual pip hint remains for security.allow_lazy_installs=false, and a
mic hint still blocks when deps are present but no audio device works.
The CLI announces the one-time engine install so the pause is explained.
2026-07-28 07:59:34 -07:00
Hermes Agent f2b065658d
tune(voice): calibrate sherpa sensitivity mapping from live TTS matrix
96-utterance TTS matrix (6 enrolled profile phrases x 4 voices/accents +
4 negative phrases x 4 voices) through the real engine: the old mapping
(default threshold 0.35) missed 3/24 positives; remapping so sensitivity
0.5 lands on sherpa's recommended 0.25 recovers 2 of 3 while keeping
0/16 false fires. Detection 23/24, routing accuracy 23/23.
2026-07-28 07:59:34 -07:00
Hermes Agent 2a35c8f0b8
feat(voice): route wake phrases to their profile — "hey <profile>" wakes that profile
One sherpa listener now enrolls every wake-enabled profile's phrase
(defaulting to "hey <profile name>") and reports WHICH phrase fired.
wake.detected gains a profile field; the desktop live-switches to the
matching profile (same path as the profile rail), opens a fresh session
there, and starts hands-free voice. The single-profile CLI/TUI print the
hermes -p switch command for foreign-profile phrases instead of
answering as the wrong profile. Opt out per listener with
wake_word.profile_routing: false.
2026-07-28 07:59:34 -07:00
Hermes Agent 567f47f01f
fix(lint): explicit utf-8 encoding on the sherpa keywords tempfile 2026-07-28 07:58:16 -07:00
Hermes Agent 0ae305ed4e
feat(voice): open-vocabulary wake phrases via sherpa-onnx KWS
New "sherpa" wake_word provider: the configured phrase is BPE-tokenized
at runtime against a small streaming zipformer KWS model (~13 MB English,
one-time download cached under HERMES_HOME), so ANY typed phrase works
with zero training — including per-profile phrases like "hey coder".

wake.sherpa lazy-dep group + [wake] extra grow sherpa-onnx/sentencepiece;
requirements probe routes per provider; sensitivity maps onto sherpa
keywords_threshold. E2E-verified on real audio (target phrase fires,
foreign phrase stays silent, reset drops buffered state).
2026-07-28 07:58:16 -07:00
Brooklyn Nicholson 9f84bc30bd
feat(voice): bundle the trained "hey hermes" model as the out-of-the-box default
From #53378: ships hey_hermes.onnx/.tflite (openWakeWord pipeline,
Apache-2.0) under tools/wakewords/, resolves the default (and hey_hermes
aliases) to the bundled file, ensures openWakeWord base feature models
are fetched for custom paths too, and updates config defaults + docs
from hey_jarvis to hey hermes.
2026-07-28 07:58:16 -07:00
Omid Saadat 5839aad13d
fix(wake-word): enforce single-owner lifecycle 2026-07-28 07:58:01 -07:00
Brooklyn Nicholson c01c3f4b28
chore(voice): tidy wake_word — drop dead SURFACES, unused np, stale docstring 2026-07-28 07:58:01 -07:00
Brooklyn Nicholson edb12bf423
fix(voice): stop wake re-fire loop and empty-transcript error spam
Two bugs surfaced by the desktop wake conversation:

1. Runaway loop: wake -> voice -> resume -> wake fired again within
   ~200ms. openWakeWord keeps its rolling feature buffer across
   pause/resume, so on resume it immediately re-scored the "hey jarvis"
   captured before the pause and re-fired, reopening a session and
   restarting voice in a tight cycle. Reset the engine buffer on every
   detector (re)start so resume begins from clean audio.

2. Empty-transcript toast: a silent re-listen returns
   success:false / "… STT returned empty transcript", which the desktop
   transcribe endpoint turned into a 400 -> thrown error -> "Voice
   transcription failed" notification on every silent gap. Treat an empty
   transcript as no-speech: return {ok, transcript: ""} so the voice loop
   quietly re-listens. Real failures still 4xx/5xx.
2026-07-28 07:58:01 -07:00
Brooklyn Nicholson d2fab75ffb
chore(voice): log wake-word lifecycle at INFO for diagnosability
The detector logged listen/detect/close at debug, invisible at the
default level. Promote listen-start, phrase-detected, stream-closed, and
the wake.start outcome (disabled / unavailable / listening) to INFO, and
log wake.detected emission, so a non-triggering setup is diagnosable from
gateway/gui.log without flipping global log levels.
2026-07-28 07:57:25 -07:00
Brooklyn Nicholson 86d5b8b90f
feat(voice): extend "Hey Hermes" wake word to TUI + desktop GUI
Makes the wake word a tri-surface feature with one configurable owner.

- wake_word.surface ("auto" | "cli" | "tui" | "gui") + shared
  wake_surface_enabled() gate consulted by every surface, so exactly one
  place owns the listener and the new session it opens.
- tui_gateway: wake.start/stop/pause/resume/status RPCs + a wake.detected
  event, sharing one server-side detector for both TUI and desktop. The
  detector yields the mic to voice.record (pause on capture start, resume
  on terminal) and to the desktop's browser mic (wake.pause/resume).
- TUI (Ink): arm wake.start on gateway.ready; on wake.detected open a
  fresh session and start voice capture.
- Desktop (Electron): arm wake.start on connect; on wake.detected open a
  fresh session.
- CLI now gates on wake_surface_enabled("cli"); /wake status shows surface.
- Tests for the surface gate; docs cover the surface knob + cross-surface.
2026-07-28 07:56:45 -07:00
Brooklyn Nicholson 5f43452e91
feat(voice): add "Hey Hermes" wake word to start a hands-free session
Adds an opt-in, on-device hotword listener for the CLI. With
wake_word.enabled (or /wake on), Hermes listens in the background for a
wake phrase; on detection it starts a fresh session, captures one
utterance through the existing voice pipeline, and answers — the
"Hey Siri" pattern.

- tools/wake_word.py: provider-pluggable detector (openWakeWord, free
  local default; Porcupine, premium) over the shared 16 kHz sounddevice
  capture path. Background daemon thread with pause/resume so it yields
  the mic during a voice turn.
- CLI wiring: startup listener (off-thread), on-wake flow, an idle
  watchdog that resumes the detector after each turn, cleanup hook, and
  a /wake [on|off|status] command.
- config.yaml wake_word section; PORCUPINE_ACCESS_KEY as an optional
  secret. Engines lazy-install via the [wake] extra.
- Hands a transcript to the input queue exactly like voice mode, so no
  system-prompt/cache mutation. No new core model tool.
- Tests (mocked, no live audio/network) + feature docs.
2026-07-28 07:56:45 -07:00
Victor Kyriazakos 6a174e9967 Merge origin/main into feat/gateway-health-diagnostics
# Conflicts:
#	cron/executions.py
#	cron/jobs.py
2026-07-28 13:09:17 +00:00
Booker 1dfe781edd
fix(skills): avoid redundant bind-mount scans (#72622)
Skip hashing active copies when the bundled origin is unchanged, build rename and optional migration indexes lazily, and reuse one optional-skill directory index per sync.

Add regression coverage for unchanged copies, deferred modification detection, lazy rename recovery, and optional provenance scans.
2026-07-28 04:24:50 -05:00
Brooklyn Nicholson 1eb5ee1eaa fix(mcp): make Figma remote OAuth work via DCR allowlist defaults
Figma's mcp.figma.com register endpoint is a client_name allowlist
(Claude Code / Codex succeed; Hermes Agent 403s) and returns a client
secret while advertising auth_method=none, then requires the secret on
token exchange. Auto-set client_name + client_secret_post for Figma
hosts, pass oauth cfg through login/add paths, force interactive OAuth
for hermes mcp login from non-TTY desktop shells, and ship a catalog
entry. Proven: hermes mcp login figma → 26 tools.
2026-07-28 00:53:16 -05:00
Teknium fab4c888ae feat(voice): say 'stop' to end a voice chat hands-free
Saying EXACTLY a configured stop phrase (default: 'stop') and nothing
else now ends the voice conversation instead of being sent to the agent
as a prompt. Match is deliberately strict — whole utterance,
case-insensitive, surrounding punctuation stripped — so 'stop doing
that and try X' still reaches the agent.

- tools/voice_mode.py: is_voice_stop_phrase() + voice.stop_phrases
  config loader (default ['stop'], [] disables, malformed config falls
  back safely).
- hermes_cli/voice.py: shared continuous loop (TUI + desktop) halts on
  a stop phrase exactly like the silent-cycle limit (fires
  on_silent_limit so every UI turns voice off); stop_continuous
  force-transcribe path swallows the phrase without counting a silent
  cycle.
- cli.py: classic CLI push-to-talk/continuous path and barge-in
  utterance path disable voice mode on a stop phrase.
- Config default voice.stop_phrases: ['stop']; docs updated.

Tests: tests/tools/test_voice_stop_phrase.py (27 tests,
sabotage-verified: loop test fails when detection is disabled);
voice suites green (110 + 44 passed).
2026-07-27 21:26:23 -07:00
Alex Fournier 14bed44c8c Reapply "feat(observability): integrate NeMo Relay runtime and shared metrics"
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 21:10:51 -07:00
Teknium fae29c8410 fix(tts): class-level .ogg container repair + multi-platform opus voice detection
Root-cause fix for the 'TTS voice bubble broken' issue family (#57048,
#54589, #57213, #58845, #14841, #45557, #57049). Two class-level defects:

1. Several backends silently write MP3/WAV bytes into a .ogg output path
   (Edge only emits MP3, Piper writes WAV, xAI writes MP3, some
   OpenAI-compatible servers ignore response_format=opus). Platforms that
   need real Ogg/Opus render 0-second/broken voice bubbles. Instead of
   per-provider patches, text_to_speech_tool now sniffs magic bytes once
   after synthesis (_sniff_audio_container) and repairs the container
   centrally (_repair_ogg_container): ffmpeg transcode in place, or rename
   to the honest extension when ffmpeg is unavailable. Covers every
   current and future provider, including command providers and plugins.

2. want_opus only recognized Telegram, so Matrix/Feishu/WhatsApp/Signal
   auto-TTS voice replies were synthesized as MP3 and delivered as broken
   attachments. New OPUS_VOICE_PLATFORMS set covers all voice-bubble
   platforms.

_convert_to_opus refactored onto a shared _ffmpeg_transcode_to_opus that
supports safe in-place transcodes (-f ogg forced muxer, temp file +
os.replace).

Tests: tests/tools/test_tts_container_repair.py (13 tests incl. a live
ffmpeg round-trip); full TTS suite green (153 + 187 passed).
2026-07-27 20:28:35 -07:00
Teknium a10bd49ddd feat(stt): unify language resolution across all STT providers
Class-level fix for the 'STT transcribes the wrong language' issue family
(#55551, #50181 and siblings). Previously language handling was per-provider
chaos: local honoured stt.local.language, Groq/OpenAI/Mistral/DeepInfra sent
no language hint at all, xAI silently forced 'en', ElevenLabs used its own
language_code key, and there was no global setting.

- New _resolve_stt_language() helper: stt.<provider>.language >
  stt.language (new global key) > HERMES_LOCAL_STT_LANGUAGE > auto-detect.
- Threaded through ALL providers: local, local_command, groq, openai,
  mistral, xai, elevenlabs, deepinfra (shared OpenAI handler), command
  providers, and plugin dispatch.
- xAI no longer forces English when nothing is configured (auto-detect).
- Mistral Voxtral now receives a language hint when configured.
- stt.groq.model is now honoured from config (previously env-only).
- DEFAULT_CONFIG gains stt.language, stt.groq, stt.xai, stt.mistral.language.
- Tests: tests/tools/test_stt_language_resolution.py (11 tests, sabotage-
  verified) + full transcription suite green (236 passed).

Builds on cherry-picked contributor work from #19786 (@zombopanda),
#23161 (@materemias), #50684 (@BlackishGreen33).
2026-07-27 20:28:31 -07:00
墨綠BG f65481674b feat(stt): pass local initial_prompt to faster-whisper 2026-07-27 20:28:31 -07:00
Mate Remias 13b52e0fa3 fix(tools): null-safe Groq STT config read
`stt.groq: null` in config.yaml yields `groq_cfg = None`, so the
subsequent `.get("language")` raised AttributeError. Use `or {}`
(matching main's widened xai/local provider guards) and add a
`{"groq": None}` regression test confirming auto-detect stays intact.

Addresses hermes-sweeper review on #23161.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_019Zc7Tgei4kav4n6WSsBq5F
2026-07-27 20:28:31 -07:00
Mate Remias be10998264 fix(tools): address Copilot review on Groq STT language hint
- Normalize stt.groq.language: cast to str, strip, treat
  empty/whitespace as unset (parity with xAI's str().strip()).
- Clarify "blank = auto-detect" inline comments in 4 docs/configs to
  reflect the env-var fallback (HERMES_LOCAL_STT_LANGUAGE).
- Document that HERMES_LOCAL_STT_LANGUAGE also drives the local
  faster-whisper provider, not just the CLI fallback.
- Add unit tests covering: omitted language when unset, config-supplied
  language, env fallback, config-over-env precedence, whitespace
  normalized to unset.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-07-27 20:28:31 -07:00
Mate Remias a355db1ef5 feat(tools): pass language hint to Groq STT
Read stt.groq.language from config.yaml (with HERMES_LOCAL_STT_LANGUAGE
env fallback) and forward it to the Groq Whisper API to skip
auto-detection on known-language audio. Omit when unset so Groq
auto-detects, preserving today's behavior. Bonus: swap xAI's hardcoded
env literal for the LOCAL_STT_LANGUAGE_ENV constant for consistency.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-07-27 20:28:31 -07:00
zombopanda af2948343c feat(stt): add language parameter support for OpenAI provider
Add optional stt.openai.language config for OpenAI transcription. Forward non-empty hints to the API while preserving auto-detection when unset. Document the config-only setting, add its default, and cover configured and unset request arguments.
2026-07-27 20:28:31 -07:00
Jeffrey Quesnelle 841a5a744a
Revert "feat(observability): integrate NeMo Relay runtime and shared metrics" 2026-07-27 22:28:08 -04:00
Alex Fournier 147e451cc8 Merge upstream main into feat/hermes-relay-shared-metrics 2026-07-27 17:54:42 -07:00
Jaaneek 5cffc53194 fix(xai): send Hermes-Agent User-Agent on chat/completions
Direct tool HTTP calls already identified as Hermes-Agent, but the main
OpenAI-SDK chat path still sent OpenAI/Python. Set Hermes-Agent/<ver> for
api.x.ai clients (xai + xai-oauth) so normal text traffic is attributed correctly.
2026-07-27 17:47:28 -07:00
Ben Barclay 981feb6730 feat(skills): org skills are editable in place; local edits survive org updates
The read-only org mirror broke the learning loop precisely where it matters
most. The system prompt tells every agent to patch a skill the moment it
finds a gap, and shared skills are the ones the most people use — but every
write to _org/ was refused, and the curator was excluded from them outright.
So org skills froze while personal skills kept improving, and the offered
alternative ("fork it into a personal skill, then propose the fork") is not
something an agent does mid-task. The refusal WAS the feature; improvements
were simply lost, and manual forks would have fragmented the shared set.

Edit in place:
- skill_manage patch/edit/write_file now work on org skills. Only delete is
  still refused (the mirror is a view of org HEAD — a local delete returns on
  the next pull; removing a shared skill is an admin action).
- Org skills are curation-eligible again, so the curator can improve the
  highest-leverage skills in the system instead of skipping them.
- The load-time provenance header now says edits are allowed and kept,
  instead of instructing the agent not to edit.

Local edits are never overwritten:
- pull_org_skills previously rmtree'd each skill dir and re-materialized it,
  silently destroying local work on the next session start. It now records a
  content fingerprint per skill (.org-baseline.json) when it writes one, and
  SKIPS any skill whose local content diverges from that baseline.
- When upstream ALSO changed such a skill, it is reported in the pull
  result's "conflicted" list and left untouched for the user to resolve
  deliberately (propose the local version, or delete it and re-pull to take
  theirs). A missing baseline is treated as unmodified so pre-existing
  mirrors do not raise phantom conflicts.
- Fingerprints are content-based (path + bytes, sorted), so a touch/mtime
  change is not mistaken for an edit.

Sharing back:
- Default: the edit stays local and the tool result tells the user to run
  "hermes skills propose <skill>".
- Opt-in sync.org_auto_propose / HERMES_SYNC_ORG_AUTO_PROPOSE submits each
  edit immediately. Defaults OFF — pushing every agent edit to a whole
  organisation is not a safe default. A failed submission never fails the
  edit; the change is saved and can be proposed later.
- "hermes sync status" lists org skills with unshared local edits;
  "hermes sync pull" reports conflicts it declined to overwrite.

Tests: 25 in the namespace suite (was 15). The two that asserted the old
read-only behaviour now assert the opposite. New coverage for edit-applied,
share-back guidance, delete-still-refused, curation-allowed, edit detection,
missing-baseline tolerance, mtime-insensitivity, and the auto-propose
default. 428 passed / 0 failed via scripts/run_tests.sh.

Verified through the REAL pull path against a mock plane: pull v1 -> edit in
place -> upstream ships v2 -> pull leaves the local edit intact, reports the
conflict, and surfaces it in status.
2026-07-28 09:08:04 +10:00
Alex Fournier 70d8db7409 Merge upstream main into feat/hermes-relay-shared-metrics 2026-07-27 15:08:25 -07:00
Teknium 731aa0ccc9 fix(browser): stop stale cdp_url from stalling every startup by 10+ seconds
Tool-schema assembly at CLI/Desktop startup runs the browser-family
check_fns (browser, browser_cdp, browser_dialog, browser_vision). Each
of those gates called _get_cdp_override(), which resolves the configured
endpoint over HTTP (GET /json/version, timeout=10) — so a *stale*
browser.cdp_url pointing at a dead debug browser cost ~7 serial blocking
socket connects before the banner rendered. Measured on a real Windows
install with a dead http://[::1]:9222 config: 15.1s of an 18s launch,
with no warning or error — just mystery slowness. The value is easy to
leave behind: /browser connect writes a session-scoped env override, but
'hermes config set browser.cdp_url' persists forever while the debug
Chrome it pointed at dies on the next browser restart.

Split the helper:

- _get_cdp_override_raw() — returns the configured value (env var or
  config.yaml) with zero network I/O. Used by every is-it-configured
  gate: check_browser_requirements, _browser_cdp_check, _is_local_mode,
  _is_local_backend, _navigation_session_key, _should_inject_engine
  (via _is_local_mode), and the hermes doctor chromium-skip check.
- _get_cdp_override() — unchanged contract (raw + /json/version
  resolution), now only called on paths that are about to connect:
  session creation and the dialog-supervisor attach.

This follows the existing rule in check_browser_requirements ('do not
execute agent-browser --version here') and the browser.manage status
path, which already banned _get_cdp_override for exactly this reason
(test_browser_manage_status_does_not_call_get_cdp_override): schema
assembly must not perform blocking I/O.

A/B on the same machine, same dead endpoint: get_tool_definitions()
15.08s unpatched -> 1.89s patched, with browser_cdp/browser_dialog
still advertised (gate now keys off configuration, not reachability —
matching the documented lazy-supervisor contract in
_browser_dialog_check).

Adds a regression test asserting the browser_cdp check_fn never touches
the network.
2026-07-27 14:32:05 -07:00
Alex Fournier 8ac686fa27 Merge remote-tracking branch 'origin/main' into fix/hermes-relay-review-round3
Signed-off-by: Alex Fournier <afournier@nvidia.com>

# Conflicts:
#	agent/chat_completion_helpers.py
2026-07-27 10:11:53 -07:00
rob-maron 02d5e23085 nous portal anthropic wire 2026-07-27 11:53:48 -04:00
Alex Fournier 4fe4b0dca7 Merge origin/main into feat/hermes-relay-shared-metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-27 08:12:37 -07:00
Ben Barclay d60d981281 fix(sync): don't require a base URL when an explicit client is supplied
pull_org_skills/propose_skill resolved and demanded HERMES_SYNC_BASE_URL
before using the caller-provided `client`, which already carries its own
base URL. Only resolve/require it on the path that actually constructs a
client.

Caught by scripts/run_tests.sh, which blanks env vars to match CI. Plain
`pytest` masked it: my shell had HERMES_SYNC_BASE_URL exported from live
testing, so the redundant check silently passed. Reproduced deliberately
with `env -u HERMES_SYNC_BASE_URL pytest` before fixing.

371 passed / 0 failed across the sync, skills, prompt, and skill-utils
suites via the canonical runner.
2026-07-27 16:44:27 +10:00
Ben Barclay 797c52b571 fix(sync): wire org skill pull into the runtime; scrub internal jargon
Two defects found by manual testing on the branch.

1. ORG SYNC NEVER RAN. The org pull/mirror/gating machinery was fully
   implemented and unit-tested but had ZERO runtime callers —
   maybe_pull_org_skills() was referenced only inside a comment, and
   `hermes sync` had no org path at all. Every code path fell through to
   personal sync (refs/user/<sub>/), so org skills never loaded and the
   feature looked like 'everything syncs to my personal org' even with a
   valid org token. The unit tests could not catch this: they invoked the
   functions directly, which is exactly the gap they left open.

   - cli.py session startup now calls maybe_pull_org_skills() alongside the
     personal maybe_pull_skills(), fail-quiet.
   - Auto-pull is gated on real org membership: resolve_org_identity()
     requires an org role on the token, only issued for multi-member orgs,
     so a solo account never reaches the network.
   - `hermes sync pull` refreshes the org mirror too (one pull, both
     surfaces) and reports what it refreshed.
   - `hermes sync status` exposes org_available/org_id/org_role/org_skills
     plus a plain-language summary, so a user can tell whether the org
     workflow applies instead of it being invisible.

2. INTERNAL JARGON LEAKED TO USERS. Help text and errors exposed internal
   milestone/spec coordinates: 'Propose a skill ... (M2)', 'Personal skill
   sync (HSP/1)', 'DEV-PHASE gate closed: your token lacks
   tool_gateway_admin', 'contract §4.3', and an inert message describing our
   internal personal-vs-multi-member design split. All rewritten in user
   language. Feature-local comments/docstrings lost their internal
   coordinates (§N, M1/M2, design.md, PR numbers) while keeping the
   explanatory prose. Pre-existing issue references elsewhere in the tree
   were deliberately left untouched.

Tests: 4 new guards, including two that assert the CALL SITES exist so the
org pull cannot silently become dead code again (verified failing when the
wiring is removed) and one that fails if user-facing help leaks jargon.
344 passed across the sync/skills/prompt suites.

Verified against live staging with a real org token: sync status reports
org_available=true, org_role=OWNER; sync pull performs the org refresh; the
.active_org marker is written with the org id from the token.
2026-07-27 16:40:16 +10:00
Tony Simons f60abd6e37 fix subagent lifecycle ownership invariants 2026-07-26 23:27:30 -07:00
teknium1 8fbe2e388f feat(tool_search): probe-validate blind tool_call args against the deferred schema
Port from nearai/ironclaw#5149 (the describe-first live-hardening fix in
their progressive tool disclosure work): when a model invokes a deferred
tool through the tool_call bridge without the schema-required arguments,
return the tool's parameter schema instead of dispatching blind.

Pre-fix, a blind call produced an opaque downstream failure
("[TOOL_ERROR] Tool execution failed: KeyError: 'document_id'") that
teaches the model nothing about what the tool expects — IronClaw observed
cheap models looping ~30 identical invalid calls until the iteration
budget died. Post-fix, the model repairs the call in one round-trip.

- tools/tool_search.py: new validate_deferred_call_args() — key-absence
  check of schema 'required' fields only; no type checking (coerce_tool_args
  already repairs types downstream); fails open on any validator error so
  it can never block a legitimate dispatch.
- model_tools.py: probe after the scope gate in the bridge dispatch.
- agent/tool_executor.py: probe in both unwrap sites (concurrent +
  sequential) before the underlying tool replaces the bridge; sequential
  path flattens the payload to match its {"error": str} wrapping.
- tests: TestDeferredCallSchemaProbe — blind call returns schema (not
  KeyError), valid/optional calls dispatch, unvalidatable tools fail open,
  out-of-scope rejection unchanged.
2026-07-26 20:59:36 -07:00
Teknium 9b97dea1e6 fix(skills): parse stored GitHub credentials without scanner false positives
Co-authored-by: Syed Annas <28944679+AnnasMazhar@users.noreply.github.com>
Co-authored-by: Bryan Neva <13835061+bryanneva@users.noreply.github.com>
2026-07-26 20:59:26 -07:00
Teknium da26ff986b fix(approval): detect recursive rm when flags follow operands
Port from openai/codex#33464: GNU rm permutes options, so
`rm build/ -rf`, `rm build/ -r -f`, and `rm build/ --recursive
--force` are equivalent to the flags-first spellings — but every
existing rm pattern required the flag group BEFORE the path, so these
spellings ran with no approval prompt at all (proven live on main).

The hardline floor was NOT affected: protected paths (/, system dirs,
$HOME) match regardless of flag position because the hardline path
matcher does not require flags. The gap was the approval-prompt layer
for arbitrary paths.

New DANGEROUS_PATTERNS entry with a tempered operand run: cannot cross
command separators (; | & newline), quotes, or a bare -- end-of-options
separator (after --, -rf is a literal filename). Flag token must be
whitespace-anchored so the r inside long options like --registry does
not count.

9 positive + 7 negative shapes in tests; approval cluster (868 tests)
green.
2026-07-26 20:58:52 -07:00
Teknium c4d1913294 fix(tools): normalize Unicode space family and minus sign in patch fuzzy matching
Port from anomalyco/opencode#38133/#38134 (patch Unicode matching corpus):
extend UNICODE_MAP with the Zs space-separator family (en/em quad, en/em/
three-per-em/four-per-em/six-per-em/figure/punctuation/thin/hair spaces,
narrow NBSP, medium mathematical space, CJK ideographic space) and the
Unicode minus sign U+2212.

Before: a file containing typographic spacing (French narrow NBSP, CJK
ideographic spaces, math minus) never matched a model's ASCII old_string
via the precise strategies — the edit only succeeded through the
similarity-based context_aware fallback, which (a) can pick the wrong
region (#54572 family) and (b) silently flattens the file's Unicode to
ASCII on replacement. After: these match at unicode_normalized (strategy
7), whose _preserve_unicode_in_replacement keeps the file's typographic
characters in unchanged spans.

All additions are 1:1 mappings, so the existing position-mapping and
preservation logic apply unchanged. Proven live before/after with a
multi-line probe; 59 fuzzy-match + 188 file-tools/patch/skill-manager
tests pass.
2026-07-26 20:58:43 -07:00
teknium1 6437701228 feat(approval): require approval for docker/podman daemon-redirect commands
Inspired by Claude Code 2.1.214, which added permission prompts for
container-CLI commands (including the Podman shim) carrying
daemon-redirect flags (--url, --connection, --identity, remote mode)
that previously ran without one.

A daemon redirect makes a local-looking command operate on a different
(often remote) daemon, silently acting on production infrastructure.
Any container-CLI invocation carrying a redirect now requires approval
regardless of subcommand:

- -H/--host and --context global flags (value required, global-flag
  position only — bare -h help and run-level -h <hostname> stay allowed)
- context use (persistently switches the default daemon)
- podman --url/--connection/--identity and -r/--remote
- DOCKER_HOST=/DOCKER_CONTEXT=/CONTAINER_HOST=/CONTAINER_CONNECTION=
  environment prefixes

Sibling-site widening: the existing container lifecycle rules matched
only the verb directly adjacent to the binary name, so a global flag or
a compose -f file flag slipped past the guard, and the legacy hyphenated
compose binary was never covered. They now tolerate global flags — the
same treatment the 'hermes ... gateway' rule already has — and match the
hyphenated compose binary.

Validation: 33 new tests; 339 pass in test_approval.py + new file;
442 pass across the adjacent guard suites; E2E battery of 12 dangerous
+ 17 safe commands via real imports, hot path ~330us/call.
2026-07-26 20:58:39 -07:00
teknium1 ece050ac30 fix(delegation): route delegated-child API calls inline to avoid nested-pool wedge (#60203)
Root cause: delegate_task children run through three nested daemon-thread
layers (async-delegation executor -> per-child timeout executor -> the
interrupt worker interruptible_api_call spawns). After multi-day gateway
uptime the deepest layer wedges BEFORE the socket opens — the same
fingerprint as the gateway-cron hang (#62151): zero stale-detector output
(the worker never reaches dispatch), all providers, foreground/restart
works. The cron fix (should_use_direct_api_call) explicitly excluded
delegation 'for lack of evidence' — #60203 is that evidence.

- should_use_direct_api_call: extend the inline gate to delegated
  children, detected via the delegation ContextVar set by
  _run_single_child (platform='subagent' stamp as fallback). Scope
  unchanged otherwise: chat_completions wire only; Codex/Anthropic/
  Bedrock/MoA keep their established workers. Interrupts still work —
  the inline path registers _active_request_abort, which interrupt()
  invokes cross-thread (same mechanism the #72227 stall monitor uses).
- _dump_subagent_timeout_diagnostic: dump ALL thread stacks (bounded,
  40), not just the conversation worker — a pre-HTTP wedge is
  indistinguishable from a slow provider without seeing where the
  nested helper threads sit.
2026-07-26 20:37:51 -07:00
embwl0x a8c9ad0bcc fix(delegate): strip URL userinfo from tool history 2026-07-26 20:36:47 -07:00
embwl0x e369d6ea3f feat(delegate): expose redacted child tool history 2026-07-26 20:36:47 -07:00
Jeffrey Quesnelle 9216198601
Merge branch 'main' into feat/hermes-relay-shared-metrics 2026-07-26 23:14:26 -04:00
HexLab98 9677495004 fix(environments): exclude multiline session env from terminal snapshots
Line-based grep on export -p only drops the first declare -x line, so a
newline in HERMES_SESSION_CHAT_NAME/USER_NAME leaves shell payload in the
shared snapshot and runs it on the next source. Unset bridged vars in a
subshell before export -p instead (issue #71296).
2026-07-26 19:30:02 -07:00
menhguin 59482ea800 fix(skills): never change a skill's source registry on update
`hermes skills update` could silently replace a same-named skill from a
DIFFERENT registry — deleting the user's files and rewriting the lockfile's
recorded provenance. Two defects on main:

- tools/skills_hub.py: check_for_skill_updates fell back to *all* sources
  (`... or sources`) when no adapter matched the recorded source, so any
  registry with a same-named skill could satisfy the fetch and be reported
  as an update — silently reassigning provenance. Now reports the entry as
  `unavailable` instead of cross-registry fallback.
- hermes_cli/skills_hub.py: do_update called do_install with a bare, slash-
  less identifier and no source constraint, letting _resolve_short_name fuzzy-
  match a same-named skill in another registry. do_install now takes an
  optional source_id pin that ABORTS (rather than falls back) when no adapter
  matches, and do_update forwards the lockfile's recorded source as that pin.

Includes regression tests reproducing the cross-registry hijack.

Salvaged from PR #72216 onto current main; re-attributed to the human
contributor.

Co-authored-by: menhguin <menhguin@users.noreply.github.com>
2026-07-26 19:29:56 -07:00
embwl0x a48251c3dc fix(update): refresh cve dependency pins 2026-07-26 19:29:07 -07:00
Vite Balloons 2a55f33483 fix(update): avoid refreshing inactive lazy backends 2026-07-26 19:28:55 -07:00
teknium1 0fa5e41c86 feat(diff): cross-surface /diff with staged/all/session modes
Widen the cherry-picked /diff base (#4839 by @SHL0MS) into one
cross-surface implementation, folding in the review feedback and the
best ideas from the two sibling PRs (#22703, #53527):

- tools/working_diff.py: shared git collection layer — unstaged
  (default), staged, and all (vs HEAD) modes; untracked files folded in
  via `git diff --no-index` so new files appear as additions (Codex
  /diff parity); shlex-split arguments preserve quoted paths.
- CLI: handler moved to hermes_cli/cli_commands_mixin.py per the
  current god-file decomposition (dispatch stays in cli.py), renders
  through the rich console with a 400-line terminal-flood guard.
- Gateway: _handle_diff_command in gateway/slash_commands.py + dispatch
  in gateway/run.py; fenced ```diff output truncated to 60 lines /
  3000 chars before the platform senders apply their own per-platform
  message clamps (tool-progress-style layered truncation). Localized
  strings in all 17 locale catalogs.
- /diff session (from #53527): cumulative checkpoint-baseline diff of
  everything Hermes changed, via new CheckpointManager.session_diff();
  docstring records the retained-baseline approximation caveat from
  review. Works on both surfaces; degrades with an actionable message
  when checkpoints are off.
- Slack: /diff routed via /hermes diff (50-slash cap; keeps
  telegram-parity test green and /version native).
- Registry: cross-surface CommandDef with staged|all|session
  subcommands; docs: slash-commands reference (CLI + gateway tables +
  both-surfaces list) and hermes-agent skill reference.
- Tests: tests/tools/test_working_diff.py (real git repos),
  tests/hermes_cli/test_diff_command.py (real git + stubbed checkpoint
  manager), tests/gateway/test_diff_command.py (end-to-end handler,
  real checkpoint store), TestSessionDiff in
  tests/tools/test_checkpoint_manager.py.

Salvaged from the /diff PR cluster #4839 + #22703 + #53527.

Co-authored-by: Ninso112 <ninso112@proton.me>
Co-authored-by: Harshkamdar67 <harshkamdar67@gmail.com>
2026-07-26 18:28:20 -07:00
teknium1 a0112ef26e feat(approvals): consecutive-denial circuit breaker for smart approvals
After N consecutive guardian denials in a session the deny message escalates to a hard-stop instruction. Inspired by ChatGPT Work auto-review circuit breaker.
2026-07-26 18:02:04 -07:00
teknium1 10b7ab5cb6 feat(clarify): extend multi-select to gateway text fallback and TUI bridge
Cross-surface coverage #23768 missed (per review feedback):

- tools/clarify_gateway.py: _ClarifyEntry carries a multi_select flag
  (register() accepts it; signature() exposes it to adapters).
  _coerce_text_response now parses multi-select replies — comma- or
  space-separated numbers ('1,3' / '1 3'), exact labels, dedup — into a
  JSON array string that _parse_multi_select_response decodes into a
  list. Out-of-range/unknown tokens reject the reply (native button UI)
  or fall back to custom text (awaiting_text/'Other' mode).
- gateway/run.py: _clarify_callback_sync accepts multi_select and
  registers it on the pending entry.
- gateway/platforms/base.py: default numbered-list text fallback tells
  the user multiple selections are allowed and how to reply.
- tui_gateway/server.py: clarify_callback passes multi_select through
  the clarify.request payload as a hint; renderers without checkbox
  support ignore the field and remain single-select-compatible.
- tests: 13 new gateway tests (flag storage, comma/space/single-number
  parsing, label matching, out-of-range rejection, dedup, end-to-end
  resolve, single-select regressions).
2026-07-26 17:46:55 -07:00
teknium1 0b670f0539 fix(clarify): route multi_select through current dispatch paths and harden callback detection
Follow-ups to the salvaged #23768 commit, which targeted a pre-79559214
codebase:

- agent/tool_executor.py + agent/agent_runtime_helpers.py: pass
  multi_select at both current clarify dispatch points (the PR's
  run_agent.py edits landed on dead code paths).
- tools/clarify_tool.py: replace the broad TypeError-retry in
  _invoke_callback with inspect.signature detection, so a compatible
  callback that raises TypeError internally is not invoked twice
  (addresses hermes-sweeper review feedback on #23768).
- tests: cover single-invocation on internal TypeError, legacy 2-arg
  callbacks, **kwargs callbacks, and registry handler multi_select
  pass-through (schema arg → handler → callback).
2026-07-26 17:46:55 -07:00
Ghislain LE MEUR 3e2f91f6b3 feat(clarify): add multi-select (checkbox) support to clarify tool
Adds a `multi_select` boolean parameter enabling checkbox-style
multi-choice questions (Space to toggle, Enter to confirm).
Backward compatible — defaults to single-select when omitted.

- tools/clarify_tool.py: schema + handler + _parse_multi_select_response
- run_agent.py: both dispatch points pass multi_select
- cli.py: checkbox UI, key bindings, rendering, edge cases
- hermes_cli/callbacks.py: TUI fallback callback
- hermes_cli/oneshot.py: oneshot multi-select message
- tests/tools/test_clarify_tool.py: 12 new tests (35 total)
2026-07-26 17:46:55 -07:00
teknium1 bd1db5460a feat(approvals): operator-customizable smart-approval policy via approvals.smart_policy
Inspired by ChatGPT Work auto-review guardian policy customization.
2026-07-26 17:46:42 -07:00
teknium1 40dc36a842 fix(deps): converge huggingface-hub on one exact version (1.24.0) across lock and lazy pin
hermes update's lazy-refresh pass re-asserts LAZY_DEPS pins whenever the
package is present (active_features() is presence-based). The
tool.trace_upload pin huggingface-hub==1.2.3 sat below transformers'
>=1.5.0,<2 requirement, so every update force-downgraded the shared
package and broke Hindsight local embeddings on daemon startup (#60783).

Keep the exact-pin security posture — no ranges — but move the pin to
1.24.0 (current) and bump uv.lock in lockstep (uv lock --upgrade-package
huggingface-hub: hub 1.4.1->1.24.0, hf-xet 1.3.1->1.5.2, click
8.3.1->8.4.2, drops typer-slim), so the entire tree converges on ONE hub
version. The refresh pass now reports 'current' with zero churn.

Invariant tests (not snapshots): the lazy pin must equal the uv.lock
resolved version, and must sit inside transformers' accepted window.
HfApi surface used by trace upload (whoami/create_repo/upload_file)
verified present with identical kwargs on 1.24.0 in a live venv.
2026-07-26 17:24:31 -07:00
teknium1 b792bd0529 feat(delegation): structured stall metadata + live per-child status in /agents
Completes #51690 on top of the salvaged #60378 timeout metadata:

- async_delegation: terminal 'stalled' events now carry structured
  stall context (stalled_after_quiet_seconds, stall_threshold_seconds,
  stall_phase idle|in_tool, stall_grace_seconds) on both single and
  batch paths, persisted in the durable row so restart-restored events
  keep it. Mirrors the sync path's timeout_seconds/timed_out_after_
  seconds/timeout_phase from #60378.
- list_async_delegations(): exposes seconds_since_progress and live
  children_activity (per-child api_calls, current_tool,
  seconds_since_activity) sampled from the dispatch's progress_fn
  outside the records lock; private monitor bookkeeping and callables
  never leak.
- /agents (CLI + gateway): background delegations render per-child
  activity rows, quiet-time hints, and the stalling state; gateway
  section is new (previously async delegations were invisible there).
  New locale key gateway.agents.background_delegations in all 17
  catalogs.

Tests: stall-metadata event shape, live-listing projection, gateway
/agents rendering (real registry dispatch, sabotage-verified), sync
timeout metadata fields, non-timeout None contract.
2026-07-26 17:13:52 -07:00
mahdiwafy 8e163852d8 fix(delegate): include explicit timeout metadata in subagent results
Add timeout_seconds, timed_out_after_seconds, and timeout_phase to timeout
results so parent agents and users can distinguish timeouts before the
first LLM call from timeouts after one or more API calls.

Also attach diagnostic_path to the N>0 API-call timeout error message,
matching the existing zero-API-call timeout path.

Addresses part of #51690 and #17308.
2026-07-26 17:13:52 -07:00
tymrtn 67826e3068 fix: scope kanban auto-subscriptions to active profile 2026-07-26 16:27:52 -07:00
Gille b93fd077c0 fix(session-search): allow scrolling compacted lineage history 2026-07-26 16:18:31 -07:00
teknium1 5f5afb1eef fix(delegation): count streamed tokens as liveness in the stale monitor
Include last_activity_ts in the progress token sampled from each child.
_touch_activity ticks on every streamed chunk ('receiving stream
response'), every tool transition, and API-call start/completion — so a
child mid-stream on a long response is alive even though api_call_count
only advances when the call completes. Same liveness signal as the
compaction inactivity budget (PR #71508): if tokens are flowing it never
dies; staleness is measured from the last streamed token / tool activity
/ API call.
2026-07-26 16:15:29 -07:00
teknium1 99a381f310 fix(delegation): progress-based stale detection for detached async runners
Replace the wall-clock timeout watchdog (from #60234) with progress-based
staleness detection, on by default with zero config:

- The async registry now accepts a progress_fn per dispatch; delegate_task
  wires a sampler over the batch's child agents (api_call_count +
  current_tool from get_activity_summary()).
- A single monitor thread sweeps running delegations: a child whose
  progress token keeps advancing is never touched, no matter how long it
  runs. A frozen token past the stale threshold (450s idle / 1200s
  in-tool, mirroring the sync-path heartbeat monitor) marks the record
  'stalling' and interrupts the child.
- A stalling child that unwinds within the grace window (120s) finalizes
  through the NORMAL path, preserving its partial results. One that never
  returns is force-finalized with a terminal 'stalled' completion event so
  the owning session hears an outcome and the async slot frees.
- Late runner returns after force-finalization are deduped by the
  begin/push/finish finalization split (kept from #60234).

Why not a timeout: delegation.child_timeout_seconds defaults to 0 by
deliberate design (DEFAULT_CHILD_TIMEOUT rationale) — a timeout-based
watchdog never arms for default configs, leaving the reported silent-
profile symptom (#60203) unfixed, and when armed it kills legitimately
slow heavy subagents mid-task. Progress detection distinguishes 'wedged
at first API call' from 'grinding through a 2h review'.

Builds on izumi0uu's finalization-atomicity work from #60234.
2026-07-26 16:15:29 -07:00
izumi0uu 65420cdecd fix(delegation): timeout stuck async child runners
Async background delegation can leave gateway sessions holding only a dispatched handle when the detached runner wedges before it can return and enqueue a completion. Enforce the configured child timeout in the async registry so the parent observes a terminal timeout event and the async slot is released.

Constraint: Issue #60203 reports long-lived gateway processes with background child delegates that never produce completion events despite child_timeout_seconds being configured.

Rejected: Relying only on _run_single_child timeout handling | it cannot finalize the async registry when the outer runner thread itself never reaches normal completion.

Confidence: high

Scope-risk: narrow

Directive: Keep background delegation completion owned by the async registry whenever detached workers can outlive the caller's immediate control.

Tested: .venv/bin/python -m pytest tests/tools/test_async_delegation.py tests/tools/test_delegate_subagent_timeout_diagnostic.py tests/tools/test_delegate.py -q

Tested: .venv/bin/python -m ruff check tools/async_delegation.py tools/delegate_tool.py tests/tools/test_async_delegation.py

Tested: git diff --check

Not-tested: Multi-day real gateway degradation; covered with deterministic stuck-runner registry tests.
2026-07-26 16:15:29 -07:00
embwl0x 1bdec6f065 fix(kanban): preserve telegram dm topic metadata 2026-07-26 16:01:32 -07:00
teknium1 920facdc4c fix(update): never blind-reinstall cua-driver during hermes update
'Refreshing cua-driver (Computer Use)...' could hang for minutes on
Windows: when the driver's native check-update verb returned an
indeterminate result (old driver without the verb, offline, GitHub
rate-limited, or the probe timing out), install_cua_driver(upgrade=True)
fell through to the full upstream installer — a silent, output-captured
run with a 660s ceiling, plus install.ps1's 600s concurrency-lock wait
on Windows on top. Every 'hermes update' paid that cost.

Two changes:

- install_cua_driver() grows require_confirmed_update: with it set, an
  indeterminate check keeps the installed version and returns fast,
  printing the force path (hermes computer-use install --upgrade).
  'hermes update' passes it; the explicit --upgrade CLI keeps the old
  fall-through so a force refresh still works when the check can't
  answer.
- cua_driver_update_check() default timeout is now 25s on Windows
  (8s unchanged on POSIX): first-spawn of the exe under Defender /
  SmartScreen routinely exceeds 8s, and a false timeout is exactly the
  indeterminate result that used to trigger the multi-minute reinstall.
2026-07-26 13:47:35 -07:00
lijun a417c6e08d fix(gateway): preserve kanban notifier chat type 2026-07-26 13:42:33 -07:00
andy 0ec1b9f7fa fix(gateway,tools): add missing .3gp and .webm to video extension sets
MEDIA_DELIVERY_EXTS in gateway/platforms/base.py omitted .3gp, causing
MEDIA: tags with .3gp files to leak as plain text instead of being
extracted for native video delivery. _VIDEO_EXTS in
tools/send_message_tool.py and _MIGRATION_VIDEO_EXTS in the Feishu
adapter omitted .webm, causing .webm files to be classified as
documents instead of video on Telegram and other platforms.

Both extensions are already present in every gateway-side _VIDEO_EXTS
definition (run.py, kanban_watchers.py, weixin.py, base.py local).

Closes #71621, Closes #71603
2026-07-26 12:52:31 -07:00
Alex Fournier 45580cc93a Merge origin/main into feat/hermes-relay-shared-metrics
Signed-off-by: Alex Fournier <afournier@nvidia.com>
2026-07-26 09:21:19 -07:00
Teknium e7172ab1ba feat(mcp): fnmatch glob support in tools.include/exclude filters
The include/exclude filter matched exact names only — glob-style entries
('*_radar_*') silently matched nothing, so a Cloudflare flat-mode config
meant to trim 3,320 tools to ~1,900 actually registered 3,319. Unmatched
patterns produced no warning.

- matches_name_filter(): exact membership first (O(1) for literal lists),
  then fnmatch.fnmatchcase for entries containing * ? [ — same pattern
  semantics as approvals.deny. Entries without metacharacters stay
  strictly literal ('docs' never matches 'docs_search').
- _should_register() uses it for both include and exclude (symmetric)
- hermes mcp tools picker (mcp_config.py) pre-selection uses the same
  matcher so the UI agrees with runtime registration

E2E against the live Cloudflare capture with the real exclude list:
3,320 -> 1,905 surviving (1,415 excluded); radar/DLP gone,
purge_cache/dns_records kept. 220/220 mcp_tool tests (4 new).
2026-07-26 08:26:09 -07:00
Teknium e9fe060ebf feat(tools): tier-2 server-summary hint + per-server listing degradation; 5% default budget
Teknium review changes on the tiered policy:

1. threshold_pct default 10 -> 5 (listing budget = min(5% of context,
   listing_max_tokens)); unknown-context fallback 20K -> 10K.

2. Tier 2 no longer leaves the model blind: when even names-only doesn't
   fit, the bridge description now carries a one-line-per-server summary
   ('cloudflare (3320 tools)') plus an instruction to search FIRST rather
   than substitute a generic tool or claim the capability is missing —
   the measured tier-2 failure mode (core-tool substitution) at zero
   meaningful token cost (~50 tokens/server).

3. Listing degradation is now PER SERVER, largest first: one oversized
   server (Cloudflare) collapses to its summary line while small
   co-attached servers (Linear) keep their full per-tool listings
   ('mixed' form). Previously global: attaching Cloudflare next to
   Linear silently cost Linear its listing. Greedy fit is deterministic
   (size then label) so the rendered block stays byte-stable per catalog
   — prompt-prefix cache safe.

E2E on real captures (defaults, 200K ctx): linear alone -> tier 1 full;
unreal alone -> tier 2 groups (5% budget) / tier 1 names at 1M;
cloudflare alone -> tier 2 groups; linear+cloudflare -> tier 1 MIXED
(linear fully listed, cloudflare summarized). 48/48 tests.
2026-07-26 08:26:09 -07:00
Teknium 7b793f7d2f fix(tools): rename provider-illegal property keys in tool schemas, reverse-map at dispatch
Cloudflare's flat API MCP ships 61 property keys that violate Anthropic's
^[a-zA-Z0-9_.-]{1,64}$ pattern (query-filter params like 'issue_class~neq'
and 'meta.<field>[<operator>]'). One bad key anywhere in the tools array
400s the ENTIRE request — measured live: Anthropic, Bedrock, Google Vertex,
and Azure all rejected an eager 3,320-tool Cloudflare request at validation,
before token limits even applied.

- schema_sanitizer: rename non-conforming property keys deterministically
  (bad chars -> '_', 64-char truncation, collision dedup with numeric
  suffixes), nested schemas included; required[] remapped alongside
- unrename_tool_args(): reverse map applied in coerce_tool_args at dispatch,
  so the MCP server receives the original wire names; recurses into object
  values and array items
- deterministic on both sides: the rename map is recomputed from the
  registry's original schema at dispatch time, no state carried

E2E on the real capture: 61 -> 0 violations across 3,320 tools; round-trip
verified on get_accounts_intel_attacksurfacereport_issues (5 '~neq' keys).
2026-07-26 08:26:09 -07:00
Teknium 0986ac393f feat(tools): tiered tool disclosure — always defer MCP/plugin tools, scale the listing with catalog size
Tier 0: no MCP/plugin tools -> everything eager (pass-through).
Tier 1: deferred tools whose catalog listing fits min(threshold_pct%
        of context, listing_max_tokens) -> bridge + skills-style
        listing, degrading to names-only over budget.
Tier 2: listing over budget even names-only (Cloudflare's flat API
        surface: 3,320 tools, names alone ~32K tokens) -> bare bridge,
        discovery through tool_search only.

The old activation threshold (defer only when schemas > threshold_pct
of context) let mid-size catalogs ride eager and pay full schema cost;
with servers like Cloudflare (~597K tokens of schema, would not even
fit a 200K window) the binary gate is the wrong shape. Activation is
now driven purely by deferrable-tool presence; threshold_pct is
repurposed as the listing budget's context-relative leg.

- AssemblyResult gains tier + listing_form for observability
- listing_max_tokens default 4000 -> 20000 (cap 60000) so an 830-tool
  catalog keeps a names-only listing while Cloudflare-scale drops to
  bare bridge
- E2E verified against real captures: Linear 24 tools -> tier 1 full,
  Epic UE 5.8 830 tools -> tier 1 names-only, Cloudflare 3,320 tools
  -> tier 2 (both 200K and 1M context)
2026-07-26 08:26:09 -07:00
teknium1 e869accc1a feat(tools): skills-style catalog listing for tool_search progressive disclosure
Deferred MCP/plugin tools become invisible once the tool_search bridge
activates — live benchmarking (48 runs, Claude Haiku 4.5) showed models
substituting visible core tools (terminal/web_search/browser) for deferred
capabilities or declaring them nonexistent instead of searching: 16/24
task success vs 24/24 with eager loading.

Skills never had this failure mode because every skill keeps a ~21-token
name+description listing line in the system prompt. This ports that exact
pattern to the tool bridge: when tool_search activates, a grouped manifest
of every deferred tool (name + first sentence of description, clipped to
60 chars, grouped per MCP server / toolset) is embedded in the tool_search
bridge description.

- tools/tool_search.py: build_catalog_listing() with deterministic
  ordering (byte-stable across assemblies -> prompt prefix stays
  cacheable); token-budget fallbacks full -> names-only -> legacy bare
  count; bridge_tool_schemas(listing=...) embeds it and instructs the
  model to skip tool_search when the exact name is visible (one fewer
  round-trip per use)
- config: tools.tool_search.listing auto|on|off (default auto),
  listing_max_tokens (default 4000, clamped 200..20000); legacy bool
  shapes keep working
- tests: 8 new tests (config parsing/clamps, short-desc clipping,
  deterministic rendering, budget fallbacks, bridge embedding, assembly
  on/off paths); full file green (47 passed)
- docs: tool-search.md config table + rationale
- scripts/tool_search_livetest2.py: benchmark harness v2 with real
  per-call token accounting (normalize_usage spy) and a third 'listing'
  mode for A/B/C comparison
2026-07-26 08:26:09 -07:00
Brooklyn Nicholson 4e49af94be fix(computer_use): stop the cua-driver child on exit
CuaDriverBackend caches a long-lived cua-driver subprocess for the life of
the Hermes process, and stop() was never called from anywhere — the driver
outlived the session that spawned it. #69903 stopped the orphan from pegging
a core by disabling the cursor overlay, but left the process behind; this is
item 3 of #28152 ("Hermes does not keep the driver alive after tool
completion").

Register an atexit hook, mirroring browser_tool's
atexit.register(_emergency_cleanup_all_sessions). atexit only, no signal
handlers, for the prompt_toolkit reason documented there. reset_backend_for_tests
now reuses the same teardown instead of repeating it.
2026-07-26 03:38:23 -05:00
webtecnica 9b909115fc fix(skills): fail closed on unknown curator ownership
- require positive agent ownership proof before any background-review mutation
- fail closed when usage record is missing, malformed, or unreadable
- preserve foreground user-directed mutations and valid agent-owned curator flows
- cover patch, edit, delete, write_file, and remove_file end to end

Closes #67073
2026-07-25 20:15:37 -07:00
Teknium 243a01d5d7 fix(curator): make the autonomous write policy consistent (#67140)
The background write guard decided ownership from `isinstance(usage_rec, dict)`,
so a local skill with NO usage record passed. That successful write called
bump_patch(), which created a `created_by: null` record — and the identical
write was refused from then on. "Allowed exactly once, then never" is a race
with our own bookkeeping, not a policy. Reproduced on main: patch #1 succeeds,
patch #2 with the same arguments is refused.

Option B from the issue. Option A (split `session_review` from
`scheduled_curator` and let the session fork patch user-owned skills it
consulted) would widen autonomous write permission onto skills the user owns
with no user present to consent — wrong direction for a no-user-present actor.

- skill_manager_tool: missing and explicit-null records now resolve
  IDENTICALLY, both fail closed. The refusal names the reason and points at
  `hermes curator adopt <name>`.
- background_review: both review prompts told the reviewer to patch any skill
  consulted in the session and claimed pinned skills could be improved, while
  enforcement refused both. Prompts now list pinned, external, and user-owned
  skills as protected, and tell the reviewer to RECOMMEND adoption instead of
  attempting a write that will be refused.
- skill_usage: document that `created_by` is a curator-management policy flag,
  not a provenance claim, and add `is_curator_managed()` so call sites read as
  the question they ask. Field name retained — it is on disk in every
  `.usage.json` and renaming would strand those records.
- curator CLI: `hermes curator list-unmanaged` itemizes unmanaged skills with
  the reason each is unmanaged (completes the #67139 spec).

Foreground writes are untouched: a user-directed edit to a user-owned skill
still works, including on pinned skills.

Sibling tests: 9 failures in test_skill_manager_tool.py were fixtures that
created record-less skills to exercise OTHER guards (consolidation-delete,
read-before-write) and relied on ownership falling through. Fixed at the
fixture, since the real curator only ever operates on managed sediment. One
test asserted the old "manually authored" wording; rewritten to assert the
behavior contract instead of the string.

Validation: 274 targeted tests + all 7 background-review files (60 tests) pass.
E2E on a temp HERMES_HOME (30 checks) covers the flip, foreground writes,
adoption unblocking, pin semantics, prompt/enforcement parity, and the new verb.
Each new test sabotage-verified: revert the fix, confirm it goes red.

Fixes #67140
2026-07-25 19:27:17 -07:00
Teknium 72de75c0ab feat(curator): surface unmanaged skills and add `curator adopt`
`hermes curator status` reported only the skills it manages, staying silent
about curation-eligible skills it can never touch. On a 237-skill library that
meant 112 skills were invisible to every automatic transition with no signal
anywhere — the curator looked broken when it was working as designed.

A skill becomes curator-managed only when `created_by: agent` lands on its
usage record, and only the background review fork writes that marker. Two
populations therefore never qualify: records written before the marker existed
(no key at all, authorship unknowable) and every foreground
`skill_manage(create)` (unset by design — those skills belong to the user).

- skill_usage: `list_unmanaged_skill_names()` / `unmanaged_report()` enumerate
  the blind spot, tagging each row with `has_provenance_key` so the two causes
  are distinguishable. `adopt_skill()` writes the marker on user declaration
  and refuses bundled, hub-installed, external, and protected built-ins.
  Adoption never resets the inactivity clock.
- curator CLI: status prints an `unmanaged (no provenance marker)` block on
  BOTH the managed and no-managed-skills paths; new `adopt` verb takes names or
  `--all-unmanaged`, with `--dry-run` and a confirmation prompt on bulk.
- skills_sync: `_backfill_optional_provenance()` matched candidates by
  repo-derived path only, so a skill installed at `mlops/chroma` that upstream
  later moved to `mlops/vector-databases/chroma` was skipped forever and
  `hermes skills repair-optional` could not fix it. Falls back to an
  unambiguous name match, still gated on identical content, and records the
  ACTUAL install path.

Provenance stays a declaration, never an inference: a high patch count proves
the agent MAINTAINS a skill, not that it authored one, since Hermes edits
user-written skills on the user's behalf routinely. An "looks agent-made"
heuristic would eventually archive hand-written work.

Validation: 347 targeted tests pass. Each new test verified via sabotage run
(revert the fix, confirm the test goes red) — one initially passed for the
wrong reason because the fixture pinned `prune_builtins` off, masking the guard
under test; fixed to force the shipped default on.
2026-07-25 18:10:24 -07:00
webtecnica b9fedab47a fix: curator labels bundled skills as agent-created (#64393) 2026-07-25 18:10:24 -07:00
teknium1 c537ae5f40 fix(skills): stop treating an upstream skill rename as a user deletion
`sync_skills()` keys the bundled manifest by frontmatter name but computes
the destination from the bundled path. When upstream renames or
recategorizes a skill, the manifest key still matches while the new dest
does not exist yet, so the loop fell into its "in manifest but not on
disk" branch and misread the skill as user-deleted: the user's copy was
stranded at the old path forever and never received another update.

Three skills hit this in the July 2026 reorg (computer-use,
evaluating-llms-harness, serving-llms-vllm) — silently frozen at their
pre-rename content on every machine that ran `hermes update`.

Recovery only moves a stale copy when it is byte-identical to the origin
hash recorded the last time sync wrote it, which proves the directory is
ours rather than the user's work. User-modified copies are kept in place
with a warning, hub-installed paths are never touched, and a genuine
deletion (no copy anywhere on disk) is still respected.

- tools/skills_sync.py: add _recover_renamed_skill() plus the
  _index_active_skills() / _read_hub_install_paths() indexes; call it
  before classification and report moves via a new `relocated` key.
- hermes_cli/main.py: surface relocations in both `hermes update` skill
  sync reporting sites.
- tests: 4 cases covering relocate, user-modified preservation,
  hub-installed exemption, and genuine-deletion respect.
2026-07-25 15:40:53 -07:00
brooklyn! 5349c7c280
Merge pull request #71162 from NousResearch/bb/session-link-titles
feat(desktop): resolve @session links to titles you can click
2026-07-25 14:03:39 -05:00
Brooklyn Nicholson efe4491666 fix(session-search): stop the agent restating a linked session's title
The old wording ("no need to also spell out the title") left the model free
to write the link on its own line and then repeat the title in the sentence,
showing the user the same session twice. Say plainly that the link IS the
title and belongs mid-sentence as a noun.
2026-07-25 12:09:36 -05:00
teknium1 95a566b1e7 fix: brace-group the filtered export dump so $BASHPID expands in the parent shell
Follow-up for salvaged PR #69380. The snippet
'export -p | grep -vE ... > $tmp.$BASHPID || true' attaches the redirect to
the grep pipeline segment, so $BASHPID expands inside grep's pipeline
subshell — a DIFFERENT pid than the parent shell that expands the follow-up
'mv $tmp' operand. The dump landed in an orphaned temp file, mv failed
silently (2>/dev/null), and the shared snapshot never updated again:
exported env / venv activation stopped persisting between commands
(tests/tools/test_local_shell_init.py TestSnapshotEndToEnd caught it).

Wrap the pipeline in a brace group and attach the redirect to the group so
the expansion happens in the current shell, matching mv's expansion. Also
rename the shell-init probe var HERMES_SESSION_ENV_PROBE ->
HERMES_STICKY_ENV_PROBE: it matched the HERMES_SESSION_ prefix the salvaged
fix now intentionally strips from snapshots, and the snippet-shape test is
updated to pin the brace-group contract.
2026-07-24 23:09:02 -07:00
bo.fu f2e32ceead fix(terminal): stop shared bash snapshot leaking HERMES_SESSION_* across sessions
A single long-lived backend serves many sessions through one
_active_environments['default'] LocalEnvironment (the messaging gateway, TUI,
and desktop/web dashboard all collapse the terminal to 'default'). That
environment persists a bash session snapshot file and sources it before every
command. 'export -p' dumped the FIRST session's HERMES_SESSION_ID into the
snapshot, so every LATER session sourced that stale value and its
'echo $HERMES_SESSION_ID' reported a FOREIGN session's id — overriding the
correct per-command Popen env injected by _inject_session_context_env.

Confirmed on staging-fp: session A read its own id, session B (same backend)
read A's id. Reproduced locally with two threads sharing one LocalEnvironment;
the snapshot held 'declare -x HERMES_SESSION_ID=...' from the first session.

Fix: strip the per-session bridged vars (HERMES_SESSION_* / HERMES_UI_SESSION_ID
/ HERMES_CRON_AUTO_DELIVER_*, i.e. gateway.session_context._VAR_MAP prefixes)
from the snapshot at both dump sites in base.py. They are re-injected fresh on
every command, so a snapshot should carry only the user's own shell state, not
Hermes' per-turn session identity.

Complements the _set_session_context session_id fix: that ensures the ContextVar
carries the right id; this ensures the shared snapshot can't override it with a
neighbour's. Adds tests/tools/test_snapshot_session_id_leak.py (regex unit +
real two-session LocalEnvironment integration) and updates the export-shape
assertions in test_base_environment.py for the new 'export -p | grep' dump.
2026-07-24 23:09:02 -07:00