Commit Graph

2652 Commits

Author SHA1 Message Date
teknium1 d1dbb0ac9e feat(gateway): multiplexer hot-serves profiles created while it runs, unroutes deleted ones
A `gateway.multiplex_profiles` gateway enumerated `profiles/` once at boot, so a profile
created afterwards (CLI, dashboard, Desktop, TUI) was never served until `hermes gateway
restart`; Desktop and the dashboard gave no reminder, so a new profile's bot simply never
connected.

The served set is now reconciled at runtime (`gateway/run_profile_reconcile.py`):
- `hermes_cli/profiles.py` create/delete ping the multiplexer over its control socket
  (new `rescan-profiles` verb); a supervised watcher rescans every 30s as the safety net.
- A new profile gets its adapters under its own runtime scope from its config/.env
  (`_start_one_profile_adapters`, same duplicate-credential guard as boot, now seeded
  with the LIVE secondaries' claims), `served_profiles` in gateway_state.json is
  updated, MCP discovery + log routing run for it. Other profiles' adapters are never
  touched.
- A served profile whose config.yaml/.env changed is re-scanned so a token added after
  create builds the adapter; already-live/queued platforms are skipped (no second poller).
- A deleted profile (tombstone) has its reconnects cancelled, adapters torn down,
  pairing/busy bookkeeping and cached agents dropped, and this process's SQLite /
  memory-store handles released so the deleter's rmtree succeeds.
- The in-process cron ticker takes a live enumerator so new profiles' jobs fire.
- PUT /api/messaging/platforms/<id>?profile=X returns `hot_served` when a live
  multiplexer rebuilt X's adapters; Desktop/dashboard skip the restart banner then.
- `hermes profile create` confirms hot-serve; the restart reminder stays for a gateway
  that did not pick the profile up (older build / signal failed).
2026-09-12 08:49:16 -07:00
teknium1 0d6b59fb74 docs(profiles): zh-Hans --clone wording matches the English correction 2026-09-12 08:48:24 -07:00
teknium1 49aed6e81c docs(profiles): --clone copies the curated memory files, not just config
The profiles guide promised "fresh sessions and memory" while
_CLONE_SUBDIR_FILES deliberately copies memories/MEMORY.md and USER.md
(curated identity, same tier as SOUL.md). State the real behaviour and how
to get a blank memory, so #10376's first half stops surprising people.

Refs #10376
2026-09-12 08:48:24 -07:00
teknium1 6c1db05d4a docs(feishu): soften 200340 causality, mirror callback-tab guidance in zh-Hans
Drop the categorical 'missing any step always means 200340' and
'200672/673 necessarily is an adapter bug' claims; the Interactive Card
toggle's role is unverified. Bring the Chinese guide in line (it still
pointed at the Event tab). Review follow-up.
2026-09-12 08:48:09 -07:00
teknium1 8ea7c0bfed docs(feishu): 200340 on card buttons is a callback-subscription gap, not a payload bug
Six issues (#10251, #10073, #13924, #38305, #25886, #8246) and four PRs
proposed json.dumps()-ing CallBackCard.data. The lark_oapi SDK types
`data` as Any and marshals the whole response with JSON.marshal(), so a
dict already reaches Feishu as the nested object the card-callback doc
shows in its response example; a string would nest a JSON *string* there
instead. Feishu documents 200340 as "the application has not configured
the card callback address or the configured request address is invalid"
— the click is rejected before delivery (nothing reaches Hermes), which
matches the reports (no gateway log, all four buttons identical).

The docs told users to subscribe to `card.action.trigger` under Event
Subscriptions; it lives under the separate Callback Configuration tab and
needs its own long-connection/URL mode and a published app version.
Spell out the four steps and map the sibling codes (200342/200343 =
unreachable URL; 200672/200673 = our payload).

Refs #10251
2026-09-12 08:48:09 -07:00
teknium1 b78abb4710 fix(config): stop forcing 0700 on HERMES_HOME inside containers
Every start (and every `ensure_hermes_home` from a sibling CLI invocation)
chmod'd the data directory to 0700, wiping group/other bits and the ACL
mask on a bind mount shared with other containers (hermes-webui, Nix
desktop + dashboard). _secure_file already skipped containers for this
reason; _secure_dir did not.

In a container the directory mode is now left to the operator unless
HERMES_HOME_MODE is set explicitly, which is still applied. cron/jobs.py
had its own 0700/0600 copies that bypassed the managed/container rules;
they now delegate to the shared helpers so cron/output stops re-locking
the mount as well.

Fixes #10757
2026-09-12 08:43:43 -07:00
teknium1 2f3ccfa3bd fix(gateway/config): promote every top-level platform key into extra
`platforms.webhook.port: 9100` (and `routes`, `secret`, api_server `key`/
`cors_origins`, any adapter setting) was silently dropped unless nested
under `extra:` — PlatformConfig.from_dict only read a fixed set of typed
fields. Two partial bridges (a per-platform port/host/secret table in the
loader and an api_server-only block) covered a few keys and had to be
extended for every new one.

from_dict now promotes every non-typed top-level key into `extra`, with an
explicit `extra:` value winning on a clash and typed fields never leaking
into `extra` on a to_dict/from_dict roundtrip. Both hand-written bridges
are removed.

Same direction as PRs #10208/#10211/#10453 (rainow's #10206 diagnosis) and
#20506; those targeted the pre-loader layout.

Fixes #10206
2026-09-12 08:42:58 -07:00
teknium1 853bfec43a docs(browser): separate Chrome 136 flag refusal from the 144+ approval dialog
The salvaged paragraph described one mechanism that is actually two.
Per developer.chrome.com/blog/remote-debugging-port, Chrome 136+ simply
stops respecting --remote-debugging-port/--remote-debugging-pipe against
the default data dir — no dialog, nothing listens. The "Allow remote
debugging?" prompt the contributor saw is the separate Chrome 144+ opt-in
approval flow (chrome://inspect/#remote-debugging), which asks per
incoming connection, not per launch. Say so, cite both sources, and keep
the fix (non-default --user-data-dir, or use_real_profile) unchanged.
2026-09-12 08:30:27 -07:00
hankookdnt d47df6ea00 docs(browser): the Chrome 136+ remote-debugging block is a consent dialog, not a silent failure
The `/browser connect` tip said Chrome 136+ "silently refuse[s] to open the
remote debugging port" on the default user-data-dir and that "there is no error
message". Chrome does surface it: on Chrome 152/macOS, launching the default
profile with --remote-debugging-port puts up an "Allow remote debugging?" dialog,
and the port opens once you press Allow. Port 9222 refusing connections is the
symptom while that consent is pending, not a permanent silent block.

Two details this cost time to rediscover, now written down:

- the consent is asked per launch, so it reappears on every browser restart
- the remote-debugging toggle in chrome://settings does not suppress it; that
  toggle only makes the feature available

Also cross-references browser.use_real_profile for the case the tip leaves
unanswered — wanting existing logins in the agent's browser. A dedicated
user-data-dir avoids the dialog but starts signed out; the real-profile snapshot
gets both, since the snapshot copy is itself a non-default user-data-dir.

Verified locally: default profile + --remote-debugging-port=9222 shows the
dialog and leaves 9222 closed, while a --user-data-dir launch answers
/json/version in under a second with no prompt.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-09-12 08:30:27 -07:00
teknium1 abedd8c018 fix(website): active filter pill stays readable on hover
The generic .filterBtn:hover rule outranks .filterActive and set the label to emphasis-1000 (near-black) on the emphasis-900 pill background, so hovering the selected filter made it unreadable in light mode and left the #91491 contrast fix incomplete. Add a .filterActive:hover rule keeping the emphasis-0 foreground. Dark mode is unaffected: [data-theme='dark'] .filterActive ties .filterBtn:hover on specificity and wins by source order.
2026-09-12 08:28:35 -07:00
teknium1 1df51cb4ee fix(dashboard,website): widen sidebar fallback to chat side panel; trim CSS comments
The chat page's mobile side panel reads the same --component-sidebar-background
skin var as App.tsx and renders transparent under skins that do not define it,
so it gets the same var(--background-base) fallback. Trim the two salvaged CSS
comments to the WHY.
2026-09-12 08:28:35 -07:00
zohuyhieuzo03 ee18a0b060 fix(website): readable filter pill labels in light mode
Active filter pills on /docs/user-stories used color: var(--ifm-background-color)
on a near-black background, but Infima's light theme resolves that variable to
transparent because custom.css only overrides it under [data-theme='dark'].
Default-active "All" pills therefore rendered as empty black blobs (#91491).

Switch to --ifm-color-emphasis-0 for theme-aware contrast. Apply the same fix to
skills page pick-button hover labels.

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-09-12 08:28:35 -07:00
teknium1 a5228204b4 fix(branding): Caduceus in the WhatsApp bridge, installers and favicon too
Review finding on #109142: the JS bridge's DEFAULT_REPLY_PREFIX (the sender
actually used at runtime), scripts/install.sh, setup-hermes.sh and the site
favicon still carried the old glyph. Python and JS defaults now agree.
2026-09-12 08:25:54 -07:00
bixycler 70d0f556d7 fix(branding): use the Caduceus ☤ (U+2624), not the Rod of Asclepius ⚕ (U+2625)
Every inline glyph — CLI banner/status bar/response labels/goodbye, setup
and doctor boxes, gateway update prompts, WhatsApp reply prefix, TUI theme,
locale strings and the docs — used ⚕, the staff of Asclepius (medicine).
Hermes carries the Caduceus ☤. The ASCII-art logo was already correct.

Mechanical swap across 60 files (no logic change); both glyphs are
East-Asian-width Neutral so no layout shifts. Skins that set their own
`response_label` / `goodbye` are unaffected.

Direction from PR #7064 (@bixycler), the earliest of #7064 / #9611 / #15574,
redone against current main.

Fixes #9565
2026-09-12 08:25:54 -07:00
teknium1 535fd88c70 fix(backup): keep durable cache/ artifacts (images, citation ledger) in full backups
Excluding cache/ wholesale at profile roots dropped media the gateway
delivered to or received from the user (cache/images, audio, videos,
documents, screenshots) and the grounded-citations evidence ledger
(cache/citations/ledger.json) — none of which can be regenerated.
Prune only the regenerable cache/<x> subtrees; keep those six.
2026-09-12 08:25:49 -07:00
teknium1 b97ae5c9b8 fix(backup): make the socket test runner-safe and document the new exclusions
The picked test bound an AF_UNIX socket at pytest's tmp_path, which overflows
the ~108-byte sun_path limit under scripts/run_tests.sh's deep temp root
("AF_UNIX path too long"). Bind by a relative name from inside the temp
HERMES_HOME instead; the walker still sees the same absolute entry.

Also list cache/ + runtime roots and non-regular entries in the `hermes backup`
"What's excluded" docs so the user-visible behaviour change is documented.
2026-09-12 08:25:49 -07:00
teknium1 44ce128a27 fix(personality): honour the top-level personalities: config block on every surface
DEFAULT_CONFIG ships a root-level `personalities: {}` (from #643) and the schema
whitelists it, but the single personality resolver read only
`agent.personalities`. A user who followed the generated config saw
"No personalities configured" from /personality on CLI, gateway and TUI.

`available_personalities()` now merges root `personalities` then
`agent.personalities` (later wins), so all three consumers pick both up.
Earlier attempt: PR #9657 (@flobo3) patched the CLI loader only.

Fixes #9636
2026-09-12 08:24:26 -07:00
Teknium 850c48cd84 feat(skills-hub): tap K-Dense and OpenScience scientific skills under one "science" bucket
~480 scientific research skills become searchable/installable through the Skills Hub
with nothing vendored: K-Dense-AI/scientific-agent-skills (165, MIT) and
synthetic-sciences/openscience (314 across 17 category paths, Apache-2.0).

A new optional tap-level `bucket` key stamps extra["category"] on every skill from a
tap whose repo ships no skills.sh.json grouping, so several repos surface as one hub
category; a sidecar grouping still wins when present. Both repos stay at community
trust (not in TRUSTED_REPOS) so the guard scans every install.

Re-grafted from #60559 onto the post-split tools/skills_hub_github.py.
2026-09-12 07:54:04 -07:00
Teknium 53c57871d6 feat(plugin-catalog): add snyk — Snyk MCP server + snyk-security-scan skill
Snyk lands as a standalone Agent Plugins v1 package
(NousResearch/hermes-plugin-snyk, pinned 2a41a07f) instead of an
optional-mcps entry: the package carries the pinned `npx -y snyk@1.1306.0
mcp` stdio launch with CLI analytics disabled AND the workflow skill that
tells the agent when to use which scanner, so a single `hermes plugins
install snyk` gives both the tools and the playbook. Third-party product
integrations ship outside the core tree per the contribution rubric.

Supersedes the optional-mcps manifest from #73860 (same pin, same
telemetry posture, tool-pruning rationale moved into the skill).
2026-09-12 06:46:17 -07:00
Teknium be2f7e9c36 feat: curator prunes unused skills at 30 days (was 90), stale at 14
A skill nobody has loaded in a month is prompt weight, not knowledge, and
archival is recoverable (`hermes curator restore`). Defaults move
stale 30→14 / archive 90→30; config v44 rewrites only the OLD defaults so
an explicitly customized window is preserved. `hermes curator prune`
now defaults --days to curator.archive_after_days instead of a
hardcoded 90 so the manual and automatic paths agree.
2026-09-12 05:56:15 -07:00
Teknium f364c19775 feat(plugins): touchdesigner ships as a catalog plugin (MCP server + skill), optional skill retired
The twozero TouchDesigner integration now lives in one installable unit:
plugin-catalog/touchdesigner.yaml points at NousResearch/hermes-plugin-touchdesigner
(portable Agent Plugins v1: mcp.json registers the twozero Streamable HTTP hub, skills/
carries touchdesigner-mcp). `hermes plugins install touchdesigner` + `hermes plugins
enable td` replaces the optional skill whose setup.sh hand-wrote an mcp_servers block.

The manifest name is `td` because Hermes names portable MCP tools
mcp__agent_plugin_<name>_<hash>__<server>__<tool>; twozero's longest tool under a
`touchdesigner` namespace is 71 chars, past the 64-char provider function-name cap.

optional-skills/creative/touchdesigner-mcp and its generated docs (bundled, optional,
zh-Hans) are removed; catalog tables, sidebar and kanban-video-orchestrator references
are updated to point at the plugin. Supersedes #68607 (MCP-catalog-only approach).
2026-09-12 05:15:22 -07:00
Siddharth Balyan b7b35a84b7 docs: remove the Nous guest free-tier guide (#108991) 2026-09-12 10:06:04 +00:00
Teknium 5c4e08e8df docs(multiplex): inbound-port platforms under the multiplexer
Replace the 'a secondary must not enable a port-binding platform' rule with the
shared-listener contract and a per-platform URL table (Twilio, LINE, Teams,
BlueBubbles, Microsoft Graph, WhatsApp Cloud, WeCom callback, Feishu webhook), plus
the status/dashboard surfaces that print the URL.
2026-09-12 01:53:15 -07:00
Teknium 6cd4fbd640 docs(cron): state the missed-occurrence contract for restart gaps
cron-internals.md gets a 'Missed-occurrence contract' section (pre-dispatch
advance is provisional, restore once, never twice, grace, opt-out, paused never
catches up, same on standalone and multiplexed); the user guide describes the
catch-up-once behaviour above the cron.catch_up_missed opt-out; cron/AGENTS.md
lists it as a hardening invariant.
2026-09-12 01:51:59 -07:00
Teknium df51797e2e feat(cron): let planned downtime skip missed recurring runs 2026-09-12 01:51:59 -07:00
Teknium be82d52cb7 docs: migrating from per-profile gateways to the multiplexer
What `hermes update` does, blockers and fixes, URL change for
inbound-port profiles, the post-create restart reminder, rollback, and
the `gateway migrate` reference row.
2026-09-12 01:49:28 -07:00
Teknium 5aa17c0590 docs(multiplex): list the newly per-profile caches in the isolation table 2026-09-12 01:35:05 -07:00
Teknium bf867d3c74 chore(skills): ship dynamic-workflow as an optional skill
Install with hermes skills install official/autonomous-ai-agents/dynamic-workflow.
Orchestration-campaign guidance is niche enough not to sit in every default prompt index.
2026-09-12 00:02:10 -07:00
Teknium fb4ed7b284 docs(skills): dynamic-workflow v2 — background-first delegation, campaign lessons from #102117
Main moved under take-1: top-level delegate_task is background-forced (results
re-enter as messages; synthesizing on the same turn reads files that do not
exist yet), per-task `toolsets` is gone (children inherit the parent's set),
DELEGATE_BLOCKED_TOOLS is {delegate_task, clarify, memory, send_message,
cronjob_manage} (execute_code is NOT stripped), and the 457-char description
was truncated by the 60-char routing budget. All four bbopen review items fixed.

Adds the campaign shape learned running the 1,863-session / 19-hour
whole-codebase simplification fan-out (#102117): shared brief + exclusive
file ownership, commit-per-step as the only handoff, fleet ceiling before the
OAuth refresh stampede, per-round integration with a frozen base and a full
suite on the combined tree, `rev-list --count` per branch before declaring a
round done (168 late-slice commits were once left behind), one serialized
test runner, forward-port last, live QA as its own wave, refuting the parent's
own heuristics with the same attempt/refuter mechanic, HANDOFF.md on restart.

Frontmatter now meets the hardline standard (platforms, ≤60-char description,
modern section order); `/tmp` replaced by the terminal temp dir so the skill is
correct on Termux and Windows. Catalog + sidebar + generated page added.
2026-09-12 00:02:10 -07:00
Teknium 284d220ba4 fix(multiplex): cron, kanban, /loop and completion paths for a served profile match its standalone gateway
Under gateway.multiplex_profiles a secondary profile X is ticked, dispatched
and notified from the default profile's process, where os.environ holds the
DEFAULT profile's .env and X's values live only in the per-turn secret scope /
HERMES_HOME override. Every remaining read that skipped that scope made X
behave differently from `hermes -p X gateway run`:

- cron: HERMES_CRON_TIMEOUT, HERMES_MODEL (job/preflight fallback),
  HERMES_CRON_MAX_PARALLEL, inflight allowance, prefill file and the script
  timeout were bare os.getenv → the default profile's values; a job without a
  model silently ran on the default's HERMES_MODEL instead of refusing.
  cron/env_settings.py::cron_env_setting reads the scope (fire) or the ticked
  home's .env (tick thread), plain environ when multiplexing is off.
- child env: the restart-safe cron worker, the Bot Chat delivery child and the
  kanban worker inherited the launch profile's non-credential .env settings
  and bridged TERMINAL_* policy (TERMINAL_ENV=docker, default's image,
  HERMES_MODEL) — X's worker ran in the default's docker image on the
  default's model. tools/environments/local.py::strip_launch_profile_env drops
  them when the child targets another served profile.
- kanban: the worker --toolsets pin was silently dropped for every served
  assignee (toolset probes call get_secret without a scope → swallowed
  UnscopedSecretError); notifier pings, artifact uploads and the wake text ran
  under the default's media policy / display language (only wake() was scoped).
- /loop: _post_turn_loop_completion hopped to the executor without contextvars,
  writing the completed tick into the DEFAULT profile's state.db and leaving
  X's row awaiting_response forever; the --until judge ran with the default's
  aux credentials.
- background processes: a secondary's processes.json (scope-relative since
  adf23550f5) was never read at startup; its processes were not re-adopted
  and notify_on_complete notices were lost. Startup recovers every served
  home under its scope; recovery adopts each session once.
- completion delivery: background_process_notifications was evaluated once per
  drain for the ambient profile (default's mode for everyone; X's `off`
  dropped a sibling's `all` event), recovered watchers used the default's
  mode, HERMES_BACKGROUND_NOTIFICATIONS was read raw from environ;
  _deliver_platform_notice used the default's GatewayConfig so a secondary's
  notice_delivery: private went public.

Not changed: gateway/run.py and tools/async_delegation.py (PR #106742
rewrites both). Known residue left for the env-bridge lane:
HERMES_SESSION_STALL_TIMEOUT is bridged once from the launch config.
scheduler bug, not a parity gap; unchanged here.
2026-09-11 19:58:07 -07:00
Teknium 9848e22ed6 feat(multiplex)!: drop gateway.multiplex_profile_allowlist — serve every profile
The multiplexing default gateway now serves default + every live named profile
under profiles/. profiles_to_serve(multiplex=True) is a pure directory read
(tombstoned profiles skipped, never mkdir); every reader — gateway served set,
/p/<profile>/ prefixes for api_server + webhook, the named-profile standalone
guard, the Desktop cron ticker (its #108428 standdown for a profile owned by a
running gateway is unchanged) — drops the allowlist parameter.

Config v43 migration deletes the key from user config.yaml; DEFAULT_CONFIG,
GatewayConfig and the top-level yaml bridge no longer carry it.

BREAKING: anyone who set an allowlist now has their excluded profiles served.
Archive or delete a profile you do not want served (Teknium approved).
2026-09-11 19:50:46 -07:00
Teknium 9c9e7ab6e5 fix(multiplex): a served profile's turn sees its own cwd, approvals, redaction and tool policy
Under gateway.multiplex_profiles a secondary profile's turn ran with the LAUNCH
profile's working directory, command allowlist, redact_secrets switch, credential
file mounts, browser engine/headed flags, LSP service, auxiliary-provider health
marks and MCP stderr log, and several TERMINAL_ENV consumers read the process env
instead of the routed profile's terminal scope. A standalone `hermes -p X gateway
run` never behaved that way.

- tools/terminal_scope.py: resolve the terminal.cwd placeholder inside the
  profile scope with the same rule gateway/run.py applies at import (local ->
  $HOME, sandbox default otherwise) so the system prompt, context files and the
  terminal of a routed turn start where the profile's standalone gateway would.
- tools/image_source.py, credential_files.py, image_generation_tool.py,
  skills_tool.py, delegate_tool_progress.py, agent/tool_executor.py: read
  TERMINAL_ENV / TERMINAL_CWD through the terminal scope.
- tools/approval.py (+ approval_floors.py): one permanent allowlist per routed
  profile home; the unscoped module set stays for single-profile processes.
- agent/redact.py: `_redact_enabled()` resolves security.redact_secrets for the
  routed profile (scope .env, then config); launch snapshot kept when unscoped.
- tools/credential_files.py, agent/auxiliary_health.py, agent/lsp/__init__.py,
  tools/browser_tool_cloud.py, tools/mcp_tool_config.py,
  tools/tool_result_storage.py: key process caches by profile home (or bypass
  the slot under an override).

Tests: tests/tools/test_multiplex_turn_parity.py (4, red on base).
Docs: multi-profile-gateways.md isolation table.
2026-09-11 19:39:12 -07:00
Teknium 446f6f79a8 fix(multiplex): dashboard and gateway stop see a served profile's gateway as the multiplexer
A profile served by the default multiplexer owns no gateway.pid / gateway_state.json,
so every surface that reads per-profile identity files called it stopped while the CLI
status surfaces (hermes -p X status / gateway status / cron status) said "running via the
default-profile multiplexer":

- `/api/status?profile=X` and `/api/messaging/platforms?profile=X` reported
  gateway_running=false / state=None / "gateway_stopped" in the same body that listed X
  under gateways[].served_profiles. The shared ladder `resolve_gateway_liveness` gains a
  fourth rung for a named profile_dir: the live default multiplexer that records X in
  served_profiles IS X's gateway (pid = multiplexer pid, runtime = its record, X's
  `<X>:<platform>` entries re-keyed to the standalone shape).
- `POST /api/gateway/stop?profile=X` spawned `hermes -p X gateway stop`, which printed
  "No gateway running for this profile" (exit 0) into the action log while the UI flipped
  to stopped and the multiplexer kept serving X; `/api/gateway/restart?profile=X` spawned
  a `-p X gateway restart` that only exits 78. start/stop now answer 409 with the
  multiplexer explanation (one helper shared with the existing start refusal) and restart
  targets the multiplexer, the process that actually serves X. A `--force`-started
  separate gateway for X (own pid file) keeps normal per-profile management.
- CLI `hermes -p X gateway stop` refuses with exit 78 like run/start/install/restart when
  X has no gateway of its own, instead of a contradictory exit-0 "not running".

Docs: multi-profile-gateways.md §1 and §5 describe stop + the dashboard behaviour.
2026-09-11 19:38:36 -07:00
Teknium 76a0c9d4c4 docs(multiplex): list adapter settings in the per-profile isolation table 2026-09-11 19:37:59 -07:00
Teknium f923faa0b8 feat(voice): GPT-Live voice chat mode — a full-duplex voice frontend that delegates to Hermes (Desktop)
`voice.voice_chat_mode: gpt-live` swaps the desktop's chained STT → turn → TTS
loop for OpenAI's gpt-live-1: one voice model that listens while it speaks and
has no tools of its own. Every real request it hears becomes a normal Hermes
turn on the open chat — any model/provider the session selected, full toolset,
memory, approvals — and the voice paraphrases the reply aloud.

Backend
- tools/voice_live.py: mode/credential/persona resolution and the one server-side
  step the API needs — POST /v1/live/sessions exchanging the renderer's SDP offer,
  pinned to client delegation; the OpenAI key never reaches the renderer. Voice
  persona follows the vendor prompting guide (role, style, labelled delegation
  policy describing Hermes as the backend). VOICE_LIVE_TURN_NOTE is the per-turn
  model-input note (transcript in, speakable prose out).
- REST: GET /api/audio/voice-live/status (mode + readiness, non-secret),
  POST /api/audio/voice-live/session (SDP exchange). The offer is passed
  byte-exact: a stripped trailing CRLF is a vendor 400 "unmarshal SDP: EOF".
- prompt.submit accepts surface=voice-live (+ voice_context) beside hud; the
  note rides the model input via the existing _prepend_note seam, the persisted
  user row stays the user's words, the system prompt stays byte-stable.
- config_defaults: voice.voice_chat_mode (chained|gpt-live), voice.gpt_live.*.

Desktop
- lib/voice-live.ts: RTCPeerConnection + oai-events data channel owner, transcript
  accumulation, session.commentary/thinking/instructions appends (500-token
  chunking), mute, graceful close waiting for session.closed.
- hooks/use-voice-live-conversation.ts: same public shape as useVoiceConversation;
  delegation → prompt.submit(surface=voice-live); tool activity → quiet thinking
  appends; reply streamed back per sentence; spoken stop phrase ends the chat;
  a newer delegation interrupts an in-flight turn.
- use-composer-voice mounts both engines and latches one at conversation start
  from the backend-resolved status; gpt-live without a key falls back to chained
  with a notice. Settings → Voice gets the mode dropdown, voice picker, persona.

Live-verified on the worktree desktop build (headless Electron, CDP, synthetic
mic): "what is 17 times 23 and which model are you on" → delegation → Hermes
(Claude Sonnet 4.5 via OpenRouter) → spoken "391 … Claude Sonnet 4.5 through
OpenRouter"; follow-up "double that" resolved from the spoken context → 782;
"run uname -r" ran the terminal tool with "Hermes is working: terminal" fed as
quiet context → spoken kernel version; "stop" closed the session
(reason=close_requested). Chained mode creates no RTCPeerConnection.
2026-09-11 19:14:24 -07:00
Teknium fafb27ee5c feat(plugins): on_room_member_activity hook projects Group Chat member runtime events to plugins
A hosted room member runs on a hidden room_plumbing session with no client
transport, so the tool.start/complete, approval.request, message.delta and
reasoning.delta frames its turn already emits bottom out at stdio and vanish.
Between turn.started and turn.settled in the durable room log a client sees a
black box, and community clients (Hermes Crew) cannot render tool cards,
approvals or live member status without inferring them from text.

One seam in write_json (plus the connector bypass in tool_progress) re-routes
those frames, stamped with the session's _hosted_room_task coordinates
(room_id, thread_id, member_id, turn_id, task_id, execution_generation), to a
new observer hook through the bounded per-consumer queues on_stream_* already
use, so plugin code never runs on the token path. Nothing is written to the
room log: deltas would exhaust a room's byte budget in minutes and checkpoint
replay must stay a pure function of the durable events. The task stamp gains
member_id (the driver already knows it; the proof did not carry it).

Group Chat keeps execution, scheduling and persistence; plugins own
presentation.
2026-09-11 19:04:58 -07:00
Teknium 27481a6338 docs(whatsapp): quoted replies attach the quoted media (both adapters) 2026-09-11 19:04:38 -07:00
Teknium bf51fee548 docs(multiplex): make the multiplexed-gateway page match what the code does
The "one gateway for all profiles" section had drifted from the runtime. Each
claim was re-verified at its defining symbol on current main and rewritten to
the behaviour users will actually see:

- named-profile guard: only `gateway run` refuses (exit 78 / EX_CONFIG,
  systemd RestartPreventExitStatus; launchd KeepAlive still retries);
  `start`/`install` do not refuse themselves and the message lands in the
  service log; `--force` is a `run`-only flag
  (hermes_cli/gateway.py::_guard_named_profile_under_multiplexer, _cmd_start)
- same (platform, token) in two profiles: the duplicate adapter is parked as
  fatal/duplicate_credential and the gateway keeps running — it was described
  as a fail-fast startup error (gateway/run_adapters.py::_refuse_duplicate_claim)
- status surfaces: one gateway_state.json under the default home with
  `<profile>:<platform>` entries + served_profiles; nothing is written under a
  secondary home (the page claimed a per-profile runtime_status.json), and
  `hermes status` does not list served profiles — `gateway list`,
  `-p X gateway status` and /api/status do (gateway/status.py::write_runtime_status,
  hermes_cli/status.py::_render_gateway, hermes_cli/gateway.py::_cmd_status)
- API_SERVER_KEY in a secondary .env auto-enables api_server and trips the
  port-binding skip; document the `enabled: false` pin
  (gateway/config_env.py::_api_server / _enable_from_env)
- allowlist: it is a start-time snapshot, and the Desktop backend's cron
  ticker enumerates every local profile regardless of it
  (hermes_cli/web_server.py::_start_desktop_cron_ticker)
- routed-profile cron via the shared bot: only when the profile has no live
  adapter of its own, and a route carrying guild_id never matches a cron
  target because delivery matches on chat_id/thread_id only
  (cron/scheduler_provider.py::tick_adapters_for,
  cron/scheduler_preflight.py::SharedRouteAdapters.get)
- add a "What is isolated per profile" table (credentials, authorization,
  endpoints, media denylist, MCP child env, outbound egress, session
  namespace, logs, terminal) describing behaviour, not PR numbers
- configuration.md: the ${VAR} scoping paragraph now says where it applies
  and links to the table
2026-09-11 15:51:11 -07:00
Teknium 819517fbac fix(gateway): routed profiles get their own max_turns, fallback chain, hooks, aux auth and media policy
One multiplexed gateway process serves every profile, but several per-turn
reads still went through state frozen from the LAUNCH profile:

- `_current_max_iterations` re-bridged `agent.max_turns`/`sessions.*` from the
  module constant `_hermes_home` into one process-wide HERMES_MAX_ITERATIONS,
  so every secondary ran with the default profile's turn budget. A routed turn
  (HERMES_HOME override) now resolves `agent.max_turns` from its own config.
- `_refresh_fallback_model` read `_hermes_home/config.yaml` into one runner-wide
  slot, so secondaries fell back through the default's provider/model with their
  own keys. It now reads the active gateway home and keeps a last-known-good
  chain per home.
- `_load_prefill_messages` resolved relative paths against the launch home.
- `agent/auxiliary_client._AUTH_JSON_PATH` was an import-time constant, so a
  secondary's compression/title/vision calls authenticated to Nous with the
  default profile's token when it had no pool entry. Resolved per call via
  `hermes_cli.auth._auth_file_path()` (patched constant still wins in tests).
- `gateway/hooks.HOOKS_DIR` was frozen at import and one `HookRegistry` was
  loaded outside any profile scope, so secondaries' `hooks/` never ran and the
  default profile's handlers received every profile's messages, responses and
  user ids. `HOOKS_DIR` now resolves per call (salvaged from #56508) and the
  runner holds one registry per served home, picked from the active scope at
  emit time and front-loaded under each secondary's startup scope.
- Shell-hook subprocesses inherited the launch `os.environ` (default HERMES_HOME
  and the default profile's secrets). They now get the routed HERMES_HOME via
  `build_subprocess_env`, scrubbed under multiplexing, and the stdin payload
  carries `profile` so one script can tell which profile fired it.
- Media-delivery policy (`gateway.strict`, `media_delivery_allow_dirs`,
  `trust_recent_files*`) was bridged once into env at startup and read from env
  per delivery; under a HERMES_HOME override the validator now reads the routed
  profile's config. Single-profile runs keep the env-bridge contract.

Audit: /tmp/mux_audit F3, F4, F6 (auth.json half), F7, F12 (media). Live repro
(temp HERMES_HOME A with profiles/B): before, B saw max_iterations 7,
fallback A/fallback, TOKEN_A, A's hooks, strict=A; after, all B's values.
2026-09-11 15:44:00 -07:00
Teknium 651878e1e4 docs(multiplex): per-profile config.yaml behaviour, env_passthrough and write guards 2026-09-11 15:29:15 -07:00
Teknium d807a34c87 docs(multiplex): cron ticker allowlist, named multiplexer, guild-scoped route delivery 2026-09-11 15:28:37 -07:00
Teknium 27768a9fa5 fix(gateway): profile_routes no longer hijack DMs to a dedicated secondary bot (#104933)
Telegram DM chat_id == user_id for every bot, so a `chat_id` route meant to
pin a user's DM with the SHARED bot to profile `ops` also captured that
user's DM with team_b's dedicated bot: the turn, session key, state.db and
secrets were ops's while the reply left via team_b's transport.

`ProfileRoute` gains an optional `bot_profile` discriminator (None = the
default profile's bot) and `matches()` requires it to equal the receiving
adapter's owner profile. `build_source` passes `_owner_profile` and stamps it
as the fallback profile for secondary adapters; `_profile_name_for_source`
derives it from the transport ref for sources built elsewhere.
Secondary→secondary routes remain possible by naming the bot explicitly.

Salvages the discriminator idea from #105040 and #105049 in a smaller shape
(no bot-username sniffing across adapter internals; the owning profile is
already declared at `set_owner_profile`).

Co-authored-by: 0xAlyDev <agentai891@gmail.com>
Co-authored-by: Ahmett101 <Ahmett101@users.noreply.github.com>
2026-09-11 15:28:00 -07:00
Teknium 37dcc0a6e8 fix(gateway): a secondary API_SERVER_KEY no longer skips the profile; start/install/status honour the live multiplexer
Under gateway.multiplex_profiles the default gateway serves every profile, yet
four startup/status paths still reasoned from the wrong source:

* A secondary profile's API_SERVER_KEY (which the docs REQUIRE for /p/<profile>/
  auth) auto-enabled api_server in that profile's config, so
  _load_secondary_profile_config raised SecondaryPortBindingConfigError and the
  whole profile was skipped. gateway/config_env.py::_enable_from_env now leaves
  `enabled` alone for port-binding platforms while a multiplexer loads a
  NON-default profile (home override + multiplex flag, the same signal
  gateway.config uses for scoped reads); the credential still lands in extra so
  the shared listener can authenticate the prefix. Default profile unchanged.

* "Is this profile served?" was re-derived from the default config.yaml plus
  GATEWAY_MULTIPLEX_PROFILES as seen by the CLI process. `hermes -p coder ...`
  loads coder's .env, so an env-only opt-in on the default profile was invisible
  (guard never fired, status said stopped) and an allowlist edit flipped the
  answer before the restart. named_profile_served_by_running_multiplexer now
  reads the pid-verified default gateway_state.json served_profiles (written by
  _record_served_profiles) first and falls back to config derivation only when
  the key is absent. The record helpers live in hermes_cli/gateway_multiplex_served.py.

* The served-profile guard ran only inside `gateway run`. `hermes -p X gateway
  start|install|restart` reached the service manager, whose unit then exited 78
  forever (systemd parks it while the CLI prints "started"; launchd KeepAlive
  respawns every 30 s). The service verbs now run the same guard up front
  (exit 78, same message) and accept --force; the Desktop /api/gateway/start
  route returns 409 for a served profile instead of spawning a doomed child.

* Status surfaces disagreed: `hermes -p coder status` said stopped, `hermes -p
  coder cron status` said "cron jobs will NOT fire" while `cron list` said fine,
  and the default `hermes status` never listed served profiles. Both now route
  through the probe / the recorded served set. The -p/--profile matcher in
  _scan_gateway_pids and gateway.status._command_line_belongs_to_profile compares
  the flag token for equality (`-p ops` no longer claims -- or lets `gateway
  stop` SIGTERM -- an `-p ops-2` gateway).

Docs: multi-profile-gateways.md now describes the start/install refusal, the
--force flags, the API_SERVER_KEY behaviour and the single default-home
gateway_state.json (the per-profile runtime_status.json claim was wrong).

Fixes #100397
Addresses #89726 #97360 #71344

(cherry picked from commit d002c1864a7b6a22c53758b16b7b0cc79aea2edf)
2026-09-11 15:27:23 -07:00
Teknium ceaf622c6d fix(mcp): same-named MCP servers with different credentials connect per profile; owner /reload-mcp keeps adopters' tools
Under gateway.multiplex_profiles every connection ledger in tools/mcp_tool.py
(_servers, _server_scope_keys/_server_tool_scopes, connecting/error/cooldown
maps, the circuit breaker, lazy schema-cache configs, trust metadata) was keyed
by the bare server NAME. The common per-tenant layout — each profile names its
server `github`/`notion` with its own token — gave only the first profile a
connection: the second profile's register_mcp_servers saw the name as "already
connected", refused to adopt it (different credentials, 4ddbcbd35e), and left
the profile silently tool-less with a healthy-looking `configured` status
(#106005 Bug 1/2, #91654). Siblings of the same bug: profile A's failing `x`
put profile B's healthy `x` into A's 10-minute connect cooldown and A's open
circuit breaker short-circuited B's calls; toolsets._resolve_toolset_memo was
not scope-keyed, so B resolved A's `mcp-<server>` tool names.

Keys are now the connection key from the new tools/mcp_tool_scope.py: the bare
name outside a multiplexer (single-profile processes are unchanged) and
(owner_scope, name) under one. Call-time lookups (_resolve_server_key) prefer
the calling scope's own connection, then a shared connection it adopted, so
identical-route profiles still share one subprocess. _select_new_servers,
the cooldown/breaker/trust maps, lazy registration and get_mcp_status all read
and write through the composite key; teardown resolves a task's key by
identity (the MCP loop has no profile context). The toolset memo key includes
registry.current_scope_key().

An owner's scoped /reload-mcp tore down its connection and, with it, every
adopting profile's tool overlay; nothing re-ran the adopters' discovery until
they reloaded. shutdown_mcp_servers(scope=) now records the orphaned adopters
and register_mcp_servers re-registers them under their own home + secret scope
once the owner's rediscovery pass completes.

Docs: multi-profile-gateways.md states the per-profile connection rule.

Fixes #106005
Fixes #91654
Co-authored-by: Bergmann89 <info@bergmann89.de>
Co-authored-by: Izzy-Gottz <srulynj@gmail.com>
2026-09-11 15:27:23 -07:00
Teknium a9838c2100 fix(multiplex): tool and memory-provider env reads stay inside the routed profile
Under gateway.multiplex_profiles, os.environ holds the DEFAULT profile's .env; a
secondary profile's values exist only in the per-turn secret scope. Every reader
below still read os.environ/os.getenv at call time, so a secondary profile's turn
silently used the default profile's value.

Credentials (F6): FIRECRAWL_API_KEY (read_file hosted OCR), OPENVIKING_API_KEY,
mem0-OSS OPENAI_API_KEY, MODAL_TOKEN_ID/SECRET and BROWSER_USE_API_KEY presence
gates, and the xAI video plugin's os.getenv("XAI_API_KEY") fallback AFTER the
scoped resolver had already missed — the exact fallback-after-miss shape
gateway/AGENTS.md forbids. Deleted, not re-scoped: the resolver is the scope.

Identity / tenant (F7): MEM0_USER_ID/AGENT_ID/HOST/MODE, SUPERMEMORY_CONTAINER_TAG,
RETAINDB_PROJECT, OPENVIKING_ACCOUNT/USER/AGENT (and the whole layered() env
read), HINDSIGHT_BANK_ID/MODE/retain shaping, HERMES_HONCHO_HOST. A raw read
put a secondary profile's memories into the default profile's account/bank/
project/tenant and recalled them back into the default's turns. Each now uses
get_secret with the provider's own per-profile default on a miss.

Endpoints (F8): OPENAI_BASE_URL (aux custom runtime + direct-alias expansion),
XAI_BASE_URL/HERMES_XAI_BASE_URL (aux OAuth), NOUS_INFERENCE_BASE_URL (#65941,
both the aux builder and hermes_cli.auth_nous._nous_inference_env_override),
GATEWAY_PROXY_URL (same UnscopedSecretError-only fallback shape as
GATEWAY_PROXY_KEY three lines below), FIRECRAWL_API_URL, BROWSERBASE_BASE_URL,
SUPERMEMORY/RETAINDB/HONCHO/HINDSIGHT URLs. The keys beside them were already
scoped, so a secondary's key was sent to the default profile's proxy or host.

Targets / display (F11): WEIXIN_HOME_CHANNEL (message posted into the default's
chat), HERMES_LANGUAGE, and agent/i18n's process-wide lru_cache of
display.language — now keyed by HERMES_HOME.

Outbound webhooks: hooks.outbound[].secret_env resolved from os.environ while
the gateway registers each profile's targets inside that profile's scope, so a
secondary's deliveries were signed with the default's secret or left unsigned.

Agent-cache eviction: _spawn_release_thread started a bare threading.Thread, so
commit_memory_session -> provider on_session_end ran with an EMPTY context. The
thread now runs copy_context() and, for the unscoped housekeeping sweep, enters
the owning profile's _profile_runtime_scope resolved from the session key
(agent:<profile>:...). The pressure batch does the same per key.

session_search (#82903): agent/inline_tool_executors.py::_session_search
forwarded every schema argument except `profile`, so a gateway agent could
never select a named profile's store. Forwarded; the ownership-scoping design
in #87779/#87847 is a separate design call and is not attempted here.

Live repro (/tmp/mux_audit/fix-tool-memory-reads/repro.py): 28 FAIL on
origin/main -> 0 FAIL with this change; 10 new invariant tests red on base.

Fixes #82903
Fixes #65941
Fixes #99121
Addresses #87779
Co-authored-by: webtecnica <75556242+webtecnica@users.noreply.github.com>
Co-authored-by: Michael Versluis (Berry) <michael@wve.nl>
2026-09-11 15:26:46 -07:00
Teknium 956793aeac docs(multi-profile): profile sessions keep their own keys and store on every gateway path 2026-09-11 15:26:09 -07:00
Teknium 759024bdff fix(deepseek): honor Flash 1M window leftovers and native vision
Users on native DeepSeek were told to pin model.context_length and
model.supports_vision in config.yaml. That is the wrong layer: the 1M
window is already in DEFAULT_CONTEXT_LENGTHS, and a global
supports_vision pin would also mark text-only deepseek-v4-pro as
multimodal.

Two catalog gaps still produced the reported symptoms:

- A leftover context_length_cache.yaml entry of 128K (the old
  ``deepseek`` catch-all) outlived the 1M catalog keys because
  deepseek-flash was missing from _PRE_CATALOG_STALE_KEYS.
- When models.dev is empty/cold, Flash has no capability record, so
  image routing falls through to lossy text. Vendor docs (2026-09-10)
  mark deepseek-flash as vision-capable and deepseek-v4-pro as not.

Discard those 128K leftovers, fill Flash (and retired Flash aliases)
via _BUILTIN_MODEL_METADATA, and leave Pro catalog-only.
2026-09-11 12:09:41 -07:00
Teknium 0dcadf6f41 revert: remove Collective Wisdom V1 (#94266)
Reverts the in-tree org skill-marketplace: hermes_wisdom package, three
model tools, CLI/gateway/desktop/dashboard/Telegram/Slack surfaces.

Later non-Wisdom work on shared files (guest onboarding i18n, dashboard
startup schema, Slack adapter, tui_gateway) is kept; Wisdom-only call
sites and config were stripped from those files.
2026-09-11 11:54:49 -07:00
Teknium cbd03e6e4c fix(gateway): secondary-profile adapters no longer inherit the default's allow-all / allowlists
Under gateway.multiplex_profiles, os.environ holds the DEFAULT profile's .env. Several
adapter-owned authorization gates still read GATEWAY_ALLOW_ALL_USERS, GATEWAY_ALLOWED_USERS
or their platform allowlist/allow-all raw from os.environ, so the default profile opting
into open access opened every secondary email/QQ/WhatsApp/Matrix/Teams/Slack/LINE/DingTalk
bot to any sender (email additionally skipped From: authentication), the default's Matrix
allowlist decided who may approve tool calls on a secondary bot, and a secondary that
opted in only in its own .env was silently deny-all.

Every such read now goes through the adapter's existing module-local scoped reader
(gateway.platforms._shared.get_scoped_secret / matrix _startup_env_secret): profile
scope first, scoped miss = default, never os.environ; the unscoped default-profile and
single-profile paths keep the environ read, where it IS the profile's own value.

Sites: email _allow_all_senders/_allowlist_in_effect; qqbot _open_dm_opted_in;
whatsapp_common _open_dm_opted_in/_live_dm_allow_from; teams _card_action_denied;
matrix _is_authorized_user, MATRIX_ALLOWED_USERS, MATRIX_IGNORE_USER_PATTERNS,
_extra_csv_set (allowed/free-response rooms); slack _slack_allow_bots/_slack_api_human_users;
line _truthy_env/allowlist (allow-all, user/group/room allowlists); dingtalk _extra_get
(allowed_users/chats, free-response chats, require_mention).

Live repro (temp HERMES_HOME, multiplex on, default env GATEWAY_ALLOW_ALL_USERS=true,
secondary scope without opt-in): EmailAdapter._allow_all_senders() True -> False,
QQAdapter._open_dm_opted_in() True -> False, Matrix _is_authorized_user('@stranger')
True -> False, Teams card action allowed -> denied.

Co-authored-by: Drexuxux <drexux0@gmail.com>
Co-authored-by: MoonsvnLyn <FirmamentalSpring@users.noreply.github.com>
Co-authored-by: svector-anu <anuoluwakolapo94@gmail.com>
Co-authored-by: babatorik <durgun.ismail@gmail.com>
Co-authored-by: salch-cred <salch-cred@users.noreply.github.com>
2026-09-11 02:24:55 -07:00
Teknium 94fb74fa97 docs(bot-mode): explain Warm Bot Backends, idle reaping, and slot waits
Fleet users read "Hermes backend for profile X exited (1)" as a crash and
raise Warm Bot Backends past their profile count to make it stop. Name the
setting, the defaults, what the exit line means, and which operations take
a slot so the knob is tuned for active bots instead of total profiles.
2026-09-11 02:23:29 -07:00