mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-11-06 13:26:40 +00:00
08f954e505cab50d6464f84ba767bdf292e8bed2
71
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Teknium
|
f219708926 |
feat(tts): fold voice search into text_to_speech's ElevenLabs schema (find_voices)
Teknium: the ElevenLabs variant of text_to_speech is where voice search belongs, not a
separate tts_voices tool. The ElevenLabs schema now carries voice_id plus a find_voices
object (text optional there); other providers' schema is byte-identical to main.
Live search findings folded in: the library is the default source and sorts by a year of
usage (most-used first); use_case (e.g. characters_animation) and sort filters; library
voices with a custom credit rate show credit_rate; the description tells the model the
library matches words literally, so a role word that finds nothing ('dwarf') falls back to
describing the sound ('gravelly old' + filters).
|
||
|
Teknium
|
c975831fbc |
feat(tts): let the agent pick ElevenLabs voices (voice_id + paginated tts_voices search)
With tts.provider: elevenlabs, text_to_speech gains an optional voice_id and a new tts_voices tool searches the user's account voices (/v2/voices) or the public Voice Library (/v1/shared-voices) with query/gender/age/accent/language filters and an opaque next_page cursor. Both are gated on the ElevenLabs provider (dynamic schema override + check_fn), so every other provider's surface is unchanged. A per-call voice_id never rewrites config; a stale one sent under another provider is ignored with a warning. |
||
|
Teknium
|
0b69853adf |
docs(browser): browser_exec is the only browser path; Camofox is a plugin
Rewrite the browser feature page, configuration, tools/toolsets/env-var/pm references, docker, windows, bot-screen, termux/installation and the secondary developer-guide/integration/feature pages (EN + zh-Hans): drop agent-browser, the built-in browser_* tools, browser.backend and /browser use; document browser.executable_path / browser.user_data_dir / browser.chromium_args and the AGENT_BROWSER_* migration; point Camofox users to 'hermes plugins install camofox'. |
||
|
alt-glitch
|
f5ea924b7e |
docs: remove the initiate-setup and first-task skills and the setup docs
Both optional skills go, and generate-skill-docs.py prunes their pages, the
optional-skills catalog rows and the sidebar entries (the sidebar would point at
missing pages otherwise). slash-commands, toolsets-reference, delegation,
tools-reference, configuration's Onboarding section and the desktop setup-chat
section return to their
|
||
|
alt-glitch
|
72e7085e9e |
feat: set_theme replaces apply_layout and reports what the desktop applied
set_theme (desktop_ui, deferred like apply_layout was) sets the accent,
light/dark mode and layout preset, or with `picker` shows an accent or
layout card and waits up to 300 s. apply_layout emitted a layout.apply
event and returned success whether or not the renderer applied anything;
set_theme asks the renderer through the theme.apply server request and
returns its answer, so an unknown preset or a chat that is not on screen
comes back as an error with the available ids.
theme.pick waits for a person; the backend tells a dismissed card
({cancelled}) from an expired one ({timed_out}). The tool description
lists the Simple and Advanced preset ids from one constant, which fixes
the old description that named neither sidebar preset. The layout.apply
event and its renderer handler are deleted with the tool.
|
||
|
Teknium
|
3bf97898ac |
perf(prompt): fixed prefix back under the post-diet size (-2.1k tokens per request)
The stock prompt surface regrew ~3.4k tokens after the August diet, almost all from features added straight into the never-deferred core. This takes back the biggest pieces: - browser_vault: the five eager browser_vault_* tools (list, fill, unlock, save_login, enter_code) become one browser_vault tool with an action enum, deferred behind tool_search by default. It still rides with the browser (an empty vault keeps save_login reachable), so discovery holds; only a catalog line is paid per request. Results and errors name the new actions; the input-tool password note points at it through tool_call. - terminal: schema re-dieted (1,136 -> 651 Qwen tokens). Description and param docs no longer repeat each other; heartbeat / persist_on_release keep their rules in one line each; process(...) references name process_manage. - tool_search / tool_call: the keyword-query rule lives once, in the queries param; description and connector hint trimmed. - system prompt: the "Async handoff" block is removed. Its rule ships in the delegate_task description and in the background dispatch result the model reads at the moment it matters, and the polling loop it targeted is guarded structurally (#124724). Stock CLI surface (prompt-surface render, chars/4): 18,612 -> 16,524. Fresh install, Qwen3 tokenizer: 14,962 -> 13,120 (Sep 7 post-diet: 11,595). Live A/B harness: evals/prefix_rediet/. |
||
|
Siddharth Balyan
|
1fad8eb3dd |
docs: multiple named connector accounts
Covers account names, no default account, the agent telling the user the name it chose, connector_alias on tools and account on results, rename, reconnect keeping the old account retired, and where to manage accounts (desktop, TUI /connectors, hermes connectors, Nous Portal). |
||
|
Teknium
|
71704ffb49 |
refactor: move Spotify out of core into the spotify catalog plugin
The spotify toolset (plugins/spotify) and its loopback-PKCE login (hermes_cli/auth_spotify.py)
now live in NousResearch/hermes-spotify, installed from the plugin catalog. Same pattern as the
Home Assistant move (
|
||
|
alt-glitch
|
8b89b68fb4 |
Merge origin/main into sid/onboarding
Brings the onboarding branch up to main |
||
|
alt-glitch
|
c2b13dc3d8 |
feat(desktop): every desktop chat can install catalog plugins; tools gated by session platform
Toolsets that exist only for one kind of session now say so on their spec:
`platforms=frozenset({"desktop"})`. `TOOLSET_SESSION_PLATFORMS` is derived
from the specs that carry the key, `all` / `*` / no selection skip those
toolsets, and `toolsets.agent_tool_drops(agent)` removes their tools from any
agent whose own session platform is not listed. `agent_init._load_tools` and
`tools/mcp_tool_agent.py` (MCP refresh and prefix restore) call that one
helper. `tool_search._DIRECT_SURFACE_TOOLSETS` is derived from
`CLIENT_SURFACE_TOOLSETS` and `TOOLSET_SESSION_PLATFORMS`.
This replaces the profile-role gate: `profile_role_toolsets`, the role code in
`_with_session_toolsets` and the explicit-pin branch, the strip step in
`_select_tool_names`, and main's `setup` toolset (whose only tool moves out)
are deleted. `manage_catalog` moves into a new `catalog` toolset, which the
desktop client folds into every desktop chat like `project` and `desktop_ui`.
It is deferred behind tool_search by default (`config_defaults` defer list).
The shared-metrics schemas' toolset enum follows (`setup` out, `catalog` in).
The install card works outside the setup chat (#129650, with review fixes):
- Parallel installs: `_set_plugin_enabled` holds a per-home lock around the
read-then-admit section, so rows enabled at once no longer refuse each other.
- A catalog plugin already on disk and not enabled is enabled in place, so Try
again after a refused enable can finish.
- A failed catalog row counts as resolved (`contract.resolves`), so it no longer
holds the turn to the 300 s deadline. The snapshot carries `resolved`, and the
card reads it instead of a hand copy of the backend's rule.
- Each card draws its own operation by op id, because models reuse call ids.
- The row carries the approved non-secret choices (`approved`: force, enable,
ref) and the chosen profile, so Try again after the card settled repeats them.
- Install phases are ids (`InstallPhase`, wire `CatalogInstallPhase`) and the
installed-row notes are fields (`enabled`, `missing_env`, `server_errors`,
`already_installed`, `requires_hermes`); the card words them in English
strings (translations follow later). Failure reasons stay raw text, and
`detail` keeps the English notes for the model.
- Installs and search target the calling chat's own home, carried as a path;
the row's profile name is only a label, with no `'default'` fallback in
Python or TypeScript.
- `dashboard_install_plugin` is split into `_resolve_source`, `_place_tree` and
`_enable_placed`.
Desktop English strings for the card move to `en_catalog_install.ts` /
`types_catalog_install.ts`, which offsets the growth of `en.ts` and `types.ts`.
|
||
|
ethernet
|
3724ace0c8 |
Merge remote-tracking branch 'origin/main' into feat/store-guest-onboarding
# Conflicts: # apps/desktop/src/app/session/hooks/use-message-stream/gateway-event/message-stream.ts # apps/desktop/src/app/session/hooks/use-message-stream/gateway-event/types.ts # apps/desktop/src/app/session/hooks/use-message-stream/index.ts |
||
|
teknium1
|
0f7a95f16d | docs: Home Assistant moves to the plugin catalog | ||
|
Siddharth Balyan
|
8feae75347 |
Apps and plugins: drop setup_choose intent, manage_catalog out of setup, cards set up later (#129245)
* fix(setup): manage_catalog leaves the setup chat; installs go to the caller's profile
- The setup profile disables the catalog toolset. The desktop session
folded it in as a client-surface toolset, so manage_catalog was still on
the setup chat's eager tool list.
- Delete default_target_profile: a catalog install and search target the
calling chat's own profile, the setup profile included.
- /initiate-setup still needs "the launch profile when run from the setup
home"; that moves to hermes_cli.setup_profile.primary_profile().
- The manage_catalog description and the reference docs drop the setup
chat exception.
* feat(setup): drop setup_choose intent; apps and plugins cards say they set up later
- setup_choose loses `intent` (the now / when needed / just note it choice)
in the tool, the wire contract and the cards. The result is
{outcome, picked}. Contracts regenerated.
- The apps and plugins pickers carry one footnote, "We'll set these up
when you start.", replacing the plugins-only "Nothing connects or
installs yet" note. Other locales translated; the desktop key list is
regenerated (it was also behind en.ts on appTour and sharedMetrics).
* fix(desktop): an install card stays drawn when a connect card follows it
The renderer keeps one connection operation per session. When a turn asks
twice (a manage_catalog install card, then a manage_connections connect
card), the second operation replaced the first in the store, and the
settled install card fell back to a plain tool row.
A settled operation that the next one replaces now moves to a store keyed
by its tool call, and the catalog and connector cards read their own row's
operation from there. Both cards stay stacked in the turn.
* fix(setup): setup_choose inline calls stop passing intent; /initiate-setup reads the launch home at call time
The inline executor still mapped intent into setup_choose_tool, which no
longer takes it, so every desktop setup_choose call raised TypeError.
primary_profile now gets server._launch_home() instead of the import-time
_hermes_home.
* fix(desktop): keep one card per kind: the latest install card and the latest connect card
The replaced-operation cache kept every settled operation by tool call, so
consecutive manage_connections calls drew one connect card each. It now
keeps, per session, only the settled operation of the other kind (install
vs connect) that the current one replaced. An install card and a connect
card stay stacked in either order, and a later call of the same kind still
takes over its card. clearConnectionRequest clears both caches, and the MCP
setup card reads the same per-row selector, so sessionConnectionRequest is
gone.
|
||
|
alt-glitch
|
14dbaec0ab |
fix(catalog): an install from the setup chat targets the launch profile
Sid's decision: the setup chat installs for the profile the user will work in, where start_chat sends the task, not into the setup profile. - default_target_profile() is the chat's own profile, except when that home carries the setup-profile marker; then it is the launch profile (server._hermes_home). Every other chat keeps the chat's own profile. - prepare() and search() use it, so the card row, the install and search's installed_in agree. The card still shows the target, and Advanced still picks another profile. - The manage_catalog description and the reference docs say where the setup chat installs. |
||
|
alt-glitch
|
b5eb5fd5c4 |
feat(catalog): manage_catalog is a desktop catalog toolset that installs into the chat's profile
manage_catalog moves out of the setup toolset into a new `catalog` toolset. Desktop sessions get it the same way they get project and desktop_ui: the client surface folds it in, TOOLSET_SESSION_PLATFORMS drops it everywhere else, and `all` does not include it. It stays a direct-surface toolset, so the default tools.tool_search.defer list (which now names manage_catalog) decides deferral and a user defer list takes control. Installs and the search's installed flag now default to the profile of the chat that calls the tool, not to `default`. The Advanced modal can still name another profile. The setup toolset stays, empty, for setup_choose. The metrics schema toolset enum gains `catalog`, and the toolsets, tools and tool-search docs follow. |
||
|
alt-glitch
|
e0e0505989 |
feat(start_chat): any desktop agent can start a visible chat through a native tool
The setup chat handed off to a new chat through about 600 lines of renderer code that always built into the default profile. This adds start_chat, a backend tool that does the same job for any desktop agent. - tools/start_chat_tool.py registers start_chat (message; optional title of at most 40 characters; optional existing profile, default the caller's own). The handler late-imports tui_gateway.start_chat. - tui_gateway/start_chat.py finds the calling session from HERMES_UI_SESSION_ID, rejects an empty message, a long title or an unknown profile, and never creates a profile. It creates the session with the caller's source and transport, inside the target profile's runtime scope, so the caller's display config does not leak into the new chat. It latches onboarding.seen.profile_build_offered in the target profile and submits the first message through prompt.submit. The call is not idempotent and keeps no receipt. - The start_chat toolset is desktop sessions only (keyed on the session platform), not in "all", not in `hermes tools`, stays direct instead of deferring behind tool_search, and is blocked for subagents. - Docs: toolsets and tools reference rows, and the subagent block list. |
||
|
alt-glitch
|
16bec86daa |
feat(setup): setup_choose asks one question or picker card in the setup chat
The setup profile needs one tool to ask the user a question or show a
picker (accent, theme, layout, connectors, plugins) as a card. Today the
runbook emits ::onboarding and ::ask directives that the app parses out
of the model's text.
setup_choose joins the setup toolset, so it is desktop-only and direct
(never deferred unless a defer list names it). It validates kind,
question and up to 12 {id, label, detail?} options, and passes
options=null through so the app can show its own list. It reaches the
renderer as a setup_choose server request, bridged in
tui_gateway/agent_callbacks.py with the clarify wait timeout. The result
reports submitted (picked, plus intent now/later/save per row for
connectors and plugins), cancelled, or no_answer. It stores nothing.
The wire contract is in tui_gateway/contracts/server_requests.py and the
apps/shared contract files are regenerated. The desktop card and fixed
lists come later. The ::onboarding/::ask directives stay for now.
|
||
|
alt-glitch
|
7182a214bb |
fix(setup): gate the setup toolset per session platform on every surface
Review follow-ups to the role deletion. - The setup toolset reached any surface that read platform_toolsets.cli (classic CLI, hermes -z, kanban workers), and "all" / "*" / a None selection pulled manage_catalog into every profile. Now "all" skips toolsets in TOOLSET_SESSION_PLATFORMS, so they arrive only when named, and agent tool loading drops their tools unless the agent's own platform is listed (toolsets.session_platform_tool_drops, applied in _load_tools and in the MCP refresh / pin restore paths). The name filter in tui_gateway's _with_session_toolsets is gone: one gate. - The focus coding posture replaced the configured list, so the guide in a code workspace lost the setup toolset. The posture path now carries the config's session-gated toolsets. - ensure_setup_profile deletes the new profile if a step after create_profile fails, so a retry does not leave unmarked orphans. - Desktop handoff recovery waits until the active session is bound to the selected guide chat, so it records the guide's profile and runtime id after the gateway swap, not the previous profile's. - Delete the renamed catalog test (lane rule) and correct the reference docs. Linear NS-1014. |
||
|
alt-glitch
|
c3f85bc54f |
refactor(setup): delete profile role; the setup profile is a marked, plain profile
The setup toolset was reserved for `role: setup` in profile.yaml, resolved by toolsets.profile_role_toolsets, and stripped from every other profile in model_tools._select_tool_names. Onboarding also wrote that role into a user's existing unmarked hermes-setup profile and adopted it, and cloned the literal default profile. Now there is no role anywhere. The setup profile carries a dot-file marker (.setup-profile.json) at its root, and onboarding finds it by that marker. A user's own unmarked hermes-setup is never touched: onboarding makes hermes-setup-<word> instead. The new profile is cloned from the launch profile, and its own config enables the setup toolset in platform_toolsets.cli. The session resolver keeps the toolset only for desktop sessions (toolsets.TOOLSET_SESSION_PLATFORMS). Copies (clone-all, import, distribution install) drop the marker, as they dropped the role. The role field also leaves ProfileInfo, the profiles.list and dashboard rows, the onboarding.ensure_setup_profile result, the gateway contracts, and the desktop ProfileInfo type. The desktop handoff recovery check no longer gates on the roster role; the guide handoff receipt keyed by the stored session already identifies the guide session. Linear NS-1014. |
||
|
alt-glitch
|
31e59b9441 |
feat: setup agent can search the catalog and install plugins and skills through the approval card
The setup profile's `setup` toolset was empty. It now carries one tool, manage_catalog: - search: catalog plugins (the Plugins tab's live catalog resolver) and hub skills, with whether each is already installed in the default profile. Read-only. - install: opens the same connection operation manage_connections opens, with rows of kind plugin / skill. Nothing installs until the user approves a row. An approved row installs into `default` (or the profile the Advanced modal named) through dashboard_install_plugin / the hub's headless install, so the catalog pin, kill list, security scan and live activation (#119644) are the host's. The row settles with the live MCP tool names and the plugin's skill. The model sends catalog ids and an action only; every other key is refused before anything runs. An unknown id or a plugin this OS cannot run is drawn failed with the installer's own text. Anywhere a catalog card cannot be drawn (TUI, CLI, messaging, registry dispatch) the result is the `hermes plugins install` / `hermes skills install` pointer. - contract: plugin/skill targets follow the MCP transitions. - run.apply_answer / reissue route a card answer to the module that owns the operation. - tool_search: `setup` joins the direct-surface toolsets, so the guide's one tool is never deferred behind tool_search. - docs: tools reference, toolsets reference, plugin catalog page. Linear NS-964. |
||
|
Siddharth Balyan
|
333898b353 |
feat: setup profile sessions get the setup toolset by profile role; nothing else can grant it (#119491)
The setup toolset (empty until NS-964 registers request_catalog_install) is reserved for the profile whose backend-written profile.yaml carries role: setup. Two points enforce it: - Grant: tui_gateway/server.py::_load_enabled_toolsets folds the in-scope profile's role toolsets into all three return paths (configured CLI toolsets, coding posture, HERMES_TUI_TOOLSETS pin), next to the client-surface set. The pin keeps it too: an operator pin picks configurable toolsets and must not strip the profile's own. - Deny: model_tools._select_tool_names strips toolsets reserved for any other role from every selection, including None/"all", a saved platform_toolsets list, profiles.configure and the env pin. That is the one point every surface's selection passes, so a default session cannot get the tool by any route. The role is read with read_profile_meta on get_hermes_home(), which under a session's home override is that session's profile dir (no directory scan). setup stays out of _HERMES_CORE_TOOLS, CONFIGURABLE_TOOLSETS and the platform-native recovery loop (it has no tools, so the loop skips it). Linear NS-963. |
||
|
treatux
|
6ae4cb88d5 |
fix(docs): reference pages name tools the registry never registered
The shipped tool-surface references still document the pre-consolidation surface: tools-reference.md lists cronjob/todo/process/project_create/ project_list/project_switch/open_preview/close_preview/read_preview/tour/tip (6 uncallable, 5 hidden dispatch-only aliases), and toolsets-reference.md still claims web_search is a member of the browser toolset — membership |
||
|
Siddharth Balyan
|
ee2f5629b8 |
Desktop connect runs on the connection operation: one card, no link to the model, no renderer polling (NS-868) (#110574)
* refactor(connectors): cut comments that restate the code
Connector modules (tools/connectors, tui_gateway connector RPCs, desktop
connector card/store) keep only comments that carry a non-derivable why or
a cross-module contract. No behaviour change.
* feat(connectors): managed connect runs on the connection operation
Managed `connect` / `reconnect` mint one ConnectionOperation for every target and, on a
desktop session, block the tool turn until the operation settles; the result is per-target
outcomes and never carries a connect link. Off the desktop the result carries the links and
returns at once (PR3 delivers them as their own message).
Why: the previous leg handed the model a URL and a `wait` verb, and the renderer ran its own
2s poller on top of the backend's 5s one; both walked the whole gateway catalog at two vendor
calls per page to read one row (~3 Composio calls/s per pending target). A hidden composer
message started the model's `wait` on the user's behalf. None of it was observable from the
operation the MCP leg already used.
What the operation looks like now:
- `contract.py`: TargetState / Actor / SettleReason enums and the `(kind, from) -> {to: actor}`
transition table. `operation.transition()` enforces it; a card cannot claim a managed
target `connected`, only the backend watcher can.
- `live.py`: one open operation per session, found by `op_id`. `connectors.operation.status`
reads it, `connection.respond` drives it, `pending_connection` on resume replays it.
- `run.py`: the one lifecycle for both target kinds (prepare -> card -> wake/observe loop ->
settle -> result). The managed `observe` hook polls the gateway list once per tick for the
whole operation; the exact-status route replaces that call when the gateway ships it.
- `connection.update` is emitted on every transition and on settlement; registered in the
shared event contract with the operation vocabulary typed on the TS side.
- `wait`, `_rendered_links`, `_seen_instructions`, the just-minted bounce and `_clamp_timeout`
are deleted. `force` on `reconnect` always reinitiates; plain `reconnect` repairs only what
the gateway reports disconnected.
- `connections.wait_timeout_seconds` is removed from config defaults, the example and the
docs. The deadline is `OPERATION_DEADLINE_SECONDS = 300` in `operation.py`; the key was
added on this unmerged train so no migration is needed.
- Wire model: `statusReason` parsed on connection results; the seven-state `connectionStatus`
is typed on list items and an unknown value fails validation; `CONNECTION_REQUIRED` carries
`connect_card_available` instead of the link when the session platform is `desktop`.
Session platform, not callback presence, decides whether a card exists: the GUI bridge
attaches callbacks to every backend session, terminal TUI included.
* feat(desktop): connector card subscribes to the connection operation
The card renders from the backend's operation instead of driving its own: `connector-flow.ts`
(the renderer's 2s `connectors.list` poller, its 120s client deadline and `keepWaiting`) is
deleted, and both hidden composer submits in `connector-tool.tsx` go with it. The model is
never nudged into a `wait`; the tool call is blocked on the backend until the operation
settles.
- `connection-request.ts` is the operation store: keyed by `op_id`, one entry per session,
`applyOperationStatus` / `applyConnectionUpdate` as pure reducers, `respond` leaves the
entry in place (the backend answers with `connection.update`), `ConnectionTargetOutcome`
is a discriminated union the backend's transition table accepts.
- `input-requests.ts` applies `connection.update`; `connection.expire` and the resume
snapshot correlate by `op_id` (a snapshot has no `request_id`).
- `ConnectorOffer` renders one `ConnectorCard` per target from a single
`Record<ConnectionTargetState, phase>` table; Connect opens the stored link, Try again on
failed / expired reissues through `connectors.connect` on the open operation, Not now is a
per-target `skipped`, Continue settles. A settled operation renders `ConnectorSummary` rows
with no live control.
- `tool-render-class.ts`: `manage_connections` renders the card regardless of
`HERMES_GUEST_ONBOARDING`; the flag still gates the onboarding flow, not the card. The
backend gate already decided admission; a card only exists because the tool was admitted.
- `mcp-setup-tool.tsx` speaks the same outcome vocabulary (connected / skipped / failed).
- `ConnectorRow.connectionStatus` is the seven-state literal union, not `string | null`.
- The guided-onboarding poller (`first-build-connectors.ts`) keeps its own row/phase types
and compiles unchanged; PR3 moves it onto the operation.
anti-slop: no net-new findings (17 touched files vs 11d1a12472).
* fix(connectors): the card never parks the tool thread; every update carries the snapshot
Found by the pre-PR adversarial review and a real-path E2E test (both left in the tree).
- The desktop `connection_callback` was still `_block("connection.request", ...)`, which parked
the tool thread on a private request-id Event until a `_respond` that no longer exists for
this event. `connection.respond` settled the operation but the tool waited its full deadline
before the watcher loop even started. The callback now only emits the card; the operation's
own wake loop is the wait. The MCP leg's blocking bridge goes with it: the card answers
through `connection.respond` like every other card.
- `connection.request` and every `connection.update` frame carry the full target snapshot
(state, link, detail). The initial mint happened before the card existed, so the renderer
never saw the links and Connect stayed disabled; a Continue settlement stamped
`not_connected` on the backend while the card still showed `initiated`. The store now
overlays the snapshot; no state is reconstructed from deltas.
- The `connection.update` emitter is a class-level `on_change` slot on the operation, set
once by `register()` (a second `register()` no longer stacks wrappers); session lookup takes
`_sessions_lock`; a re-minted link on an `initiated` target goes through `refresh_link()`
and emits, instead of a bare attribute write.
- `session.interrupt` is checked before the first observe, so an interrupted call settles
`interrupt`, not `all_resolved`.
- A gateway list reporting `expired` for an initiated target is recorded with actor `clock`
(the contract's owner of that edge); it raised `IllegalTransition` before.
- Dead `keepWaiting` i18n keys from the deleted renderer poller removed.
tests/tui_gateway/test_connector_operation_e2e.py runs the desktop lifecycle through the real
tool, registry, gateway RPC handlers and callback bridge with only the HTTP client faked.
* docs(connectors): prompts and docs describe the operation, not the deleted wait verb
The onboarding prompts told the model to call action="wait" with timeout_seconds and to
expect a hidden [setup]/[connectors] note; both are gone. tool-search.md and
toolsets-reference.md said the model gets a connect link on the desktop. tui_gateway/AGENTS.md
gains the connection-operation row of the surface table.
* fix(connectors): the panel re-mints only a dead link
Try again on a failed or expired target mints a fresh link on the open operation. A waiting
target keeps the link it was minted with; the card reopens it and connectors.connect refuses
to spend a second mint (LINK_STILL_VALID). The unused refresh_link() goes. The package
docstring names the new siblings; the nine-name public surface is unchanged.
* test(connectors): the local-batch test answers the operation the way the card does
The callback stopped returning an answer in f782b26d98 (the card answers through
connection.respond); this test still returned one and waited out the 300s deadline in CI.
* ci: retrigger
* fix(connectors): the desktop card appears outside guided onboarding
Live on a signed-in macOS desktop, the two-app connect never showed a card. Three
defects, each hidden by a test that bound state the running app never binds.
The backend read the surface from HERMES_SESSION_PLATFORM only. The desktop and TUI
gateway bind it as HERMES_SESSION_SOURCE (_set_session_context), so session_platform()
was "" and managed connects took the off-desktop branch: links in the model's message,
no operation. session_platform() now reads platform, then source. The E2E test binds
through server._set_session_context instead of set_session_vars(platform="desktop").
The renderer routed manage_connections to the card only under isOnboardingEnabled(),
the HERMES_GUEST_ONBOARDING launch flag, in message-parts.tsx and the run splitter in
fallback.tsx. tool-render-class.ts had already dropped that gate in this PR; the two
routers had not. Both now route on the tool name alone.
ConnectorTool resolved the session owner by the runtime id. Owner routes, hints and
session rows are keyed by the stored id, so in registry topology the owner never
resolved and the card rendered null while the tool blocked. It now resolves by the
stored id, matching the PR1.5 card and every other owner lookup.
message-parts-connectors.test.tsx mounts the real Fallback router with the onboarding
flag off and distinct runtime/stored ids; red before each renderer fix, green after.
* style(connectors): shorter comments, no module mock in the card router test
The router test mocked isOnboardingEnabled to false; jsdom has no preload bridge, so the
real function already returns false. Comments that restated the code are cut to one line.
anti-slop: no net-new findings (25 touched files)
* fix(connectors): Connect on a waiting row opens the stored link
ConnectorCard derived the button's loading state from the phase label, so a managed row that
read "Finish connecting in your browser" (every row, since links are minted up front) had a
disabled Connect button. Nothing on the desktop could open the sign-in link; every managed
connect ended skipped, not_connected, or at the deadline.
The card now takes `busy` for "the action itself is running" and keeps `phase` as a label.
The MCP card passes its in-flight flag; the connector card passes the re-mint wait. Red before:
the Connect button on an initiated row rendered disabled and a click opened nothing.
* fix(connectors): a settled card stays dead; the card binds to its tool call only
A second connect for the same apps revived the finished card on the old tool row. The
connection.request payload carried no id, so the renderer fell back to matching rows by
connector names, and any row with those names qualified, settled or not.
The operation now records the model's tool_call_id and sends it in connection.request and in
the resume snapshot. The card binds to the tool row with that id and to nothing else; the
name-match fallback is deleted. A payload without the id is rejected by the store.
`reason` is removed from the tool: it was the only text the card ever showed from the model
and its absence forked a second tool part, since `reason` doubled as the row-correlation key
in tool-parts.ts. The card never needed it.
`connection.expire` is deleted from the contract and from _EXPIRING_REQUESTS: the card is
raised with _emit, not _block, so nothing has emitted it since the operation lifecycle landed.
Sid's rule of record: a resolved card is fully dead; no path brings it back.
* fix(connectors): the watch loop settles once, on time, and never raises into the result
Three findings from the live review, one loop.
Continue racing a finished sign-in: the loop ran the gateway read, then settled. A read that
returned `connected` for an already-settled or failed target raised IllegalTransition out of
the tool and the model got a generic error instead of the per-app outcomes. The read now skips
targets that are not live (pending, initiated) and skips a settled operation; the loop checks
`settled` after every read.
Settle reason as row text: `settle()` wrote `continue`/`deadline` into each unresolved target's
`detail`, and the card printed it in red. The reason stays on the operation only.
Stop and the deadline waited for the next tick: `/stop` sets a per-thread flag with no wake
hook, so the sleep is sliced at 250 ms and the flag and clock are read each slice. The clock is
also checked before each read, not only after.
Tests: a failed mint that later reads connected settles cleanly; Continue during a read keeps
the settled result; no reason in detail; an interrupt settles within the same second.
* fix(connectors): MCP setup off the desktop returns unavailable instead of blocking
run_mcp_operation treated a non-None connection_callback as "a card exists". Every tui_gateway
session has that callback, the Ink TUI included, so an MCP install from the terminal UI blocked
until the 300 s deadline while the docs promised `unavailable` with the terminal commands.
The MCP path now reads the session surface the same way the managed path does; the callback is
never the predicate. Test binds the surface to `tui` with the callback attached.
* fix(connectors): a failed Try again shows the failure, not the old dead link
The panel's re-mint ignored the gateway's per-app status and moved the row to `initiated` with
whatever link came back, `None` included, so a mint that failed again rendered as waiting on the
link that had already died.
One reader of a mint response now serves both the first mint and Try again
(`managed.mint`, with the actor as a parameter). A repeated failure keeps the row `failed`,
drops the link, and carries the vendor's new text through `operation.refresh`, which emits a
frame without a state change so the card redraws.
* fix(connectors): a forced reconnect waits for the new sign-in before it reports connected
`reconnect` with `force: true` is the account switch. The vendor keeps the old account active
while the new link waits, so the first list read after the mint said `connected` and the
operation settled at once: the new link was dropped and the model was told the switch was done.
A forced target is marked awaiting_new_attempt after the mint. The watcher ignores its row until
the list shows the new attempt (`connectionStatus: initiated`) once, then trusts `connected`.
* fix(connectors): the operation registers under the gateway session key
The tool registered the operation under the agent's session_id; every RPC (connection.respond,
connectors.operation.status, the panel's connectors.connect) and the update emitter looked it up
by the gateway's session key. Those agree until compaction rotates the agent id mid-turn; then
the card's clicks find nothing, no update reaches it, and the tool waits out the deadline.
The registration key is now the bound HERMES_SESSION_KEY, with the agent id as the fallback for
callers with no gateway (unit tests, a bare CLI). The E2E passes a rotated agent id and drives
the card by the gateway key.
* fix(connectors): the forced-reconnect gate reads any non-active row; a failed re-mint of an expired row is failed
Three follow-ups from the verification of the fix pass.
The awaiting_new_attempt gate cleared only on the literal `connectionStatus: initiated`. The
field is optional on the wire and `initializing`, `failed`, `expired` are valid values, so a
forced reconnect could wait the full 300 s and swallow a failed new attempt. The gate now holds
only while the row still reads as the old account (`connected` or `active`) and releases on
anything else.
Try again on an `expired` row whose re-mint fails raised IllegalTransition (no expired → failed
edge). The re-mint steps through `initiated` as the user's attempt, then `failed`, then drops the
dead link.
`detail` never carries a state name any more: `failed` as detail rendered as the row label and
made agent/display.py tag the settled result as a tool error. Only vendor text goes there.
`connection.expire` removed from the renderer's unscoped-stream set; nothing emits it.
|
||
|
Siddharth Balyan
|
e0ef0eb9c3 |
manage_connections covers local MCP servers; setup_mcp leaves the schema (NS-867, PR1) (#109517)
* feat(connections): manage_connections covers local MCP servers; setup_mcp leaves the schema
One model tool now connects the user to apps of both kinds. A target
`{"name": "linear", "mcp": true}` is a locally configured MCP server;
`install` / `enable` / `authorize` are its verbs. Bare strings and
`{"name": ...}` stay managed connectors and that leg is unchanged.
MCP targets run through one backend-owned connection operation
(tools/connections_tool_operation.py): created with a server-side
deadline from the new config key `connections.wait_timeout_seconds`
(default 120, floor 5, no ceiling), per-target state, and exactly-once
settlement (all resolved / Continue / deadline / interrupt). Unresolved
targets freeze as `not_connected` with the settle reason.
Why the fold works now: the approval card is reached through
`agent.connection_callback` via the agent-level inline executor table,
which is the only path that carries a GUI callback. Registry dispatch
(every non-GUI surface) settles MCP targets as `unavailable` with the
`hermes mcp install / login` hint; managed targets in the same call
are unaffected.
`setup_mcp` is removed from every advertised toolset and from the
deferral list; an inline-table shim keeps calls from conversations
opened before this change dispatching (prompt-cache protection).
`_LEGACY_TOOL_ALIASES` is not the mechanism: inline tools bypass it.
Gateway: `mcp.setup.request/respond` are replaced by
`connection.request/respond/expire` (no wire compat; desktop ships
with this). The bridge waits exactly the operation's deadline. The
`session.resume` snapshot gains `pending_connection` so a reopened
window restores the card with the original deadline.
`manage_connections` joins `_SEQUENTIAL_DEADLINE_EXEMPT_TOOLS`: the
operation owns its wait; the 420s guard must not report `tool_timeout`
while the card is live.
The portal `check_fn` on the tool is dropped in favour of a
handler-level gate on the managed leg, so signed-out sessions can still
approve local MCPs.
* wip(desktop): connection.request store, resume restore, card routing for MCP targets
Renderer half of the setup_mcp fold, first slice: connection-request store
(mirrors clarify), connection.request/expire handling, pending_connection
resume restore, mcpTargets() + isCardTool(name, args) so MCP-target
manage_connections calls classify as cards. Not yet: the card component
rewrite (mcp-setup-tool.tsx), mcp-directory.ts removal, vitest, docs.
Does not typecheck until the card rewrite lands.
* fix(config): hermes update turns on the connections toolset for saved toolset lists
`hermes tools` writes an explicit `platform_toolsets.<platform>` list, and the
resolver reads absence from that list as "unchecked". The `connections`
toolset (#106842) shipped after most users last saved, so `manage_connections`
is stripped from the schema on every install that ever opened the picker.
The Nous entitlement gate never runs; the agent reports the tool as missing.
Migration 44 -> 45 (renumbered when folded into #109517; main was already at 44) appends `connections` to each explicit per-platform list
that lacks it and records the offer in `known_builtin_toolsets` where that
record exists, so a later uncheck reads as a decline. It skips: platforms
whose record already holds `connections` (the user saw the checkbox and left
it off), bare composite lists ([hermes-cli]) that already inherit it, platforms
where the toolset is not allowed, and any config whose `agent.disabled_toolsets`
names `connections` (Blank Slate, `hermes tools --disable`), because the
resolver subtracts that list last and the enable would never take effect.
The explicit-list test is the resolver's own: any configurable or plugin key.
`hermes update` runs migrations post-pull for the active profile and every
sibling, so one update is enough. Fresh installs and composite users were
never affected.
* refactor: anti-slop pass on the desktop slice; shorten added comments
Parse connection.request at the boundary with a typed wire interface instead of
unknown + typeof; mcpTargets reuses connectorText; comments cut to one or two
lines. slop-ratchet: no net-new findings in 13 touched files.
* feat(desktop): the MCP approval card answers manage_connections; MCP Directory removed
The existing card (mcp-setup-tool.tsx) now reads the connection-request store,
renders for manage_connections calls with mcp:true targets, answers through
connection.respond with a per-target outcome, and no longer calls reload.mcp
after Install; the new server's tools arrive on the between-turns refresh.
A settled operation renders the first target's frozen state.
session.resume restores a pending card with its original deadline on both the
activate and cold-resume paths.
lib/mcp-directory.ts is deleted along with its two fallback branches
(suggestion provider, card install). The catalog was already primary in both;
a catalog miss now yields no suggestion / a notInCatalog error. The GitHub
never-suggest test is rewritten on catalog-shaped data.
vitest: connection-request store (6), suggestion provider, clarify restore.
slop-ratchet: no net-new findings in 19 touched files.
* chore: drop __pycache__ files swept in by an over-broad git add
* fix(desktop): correlate the connection.request row with the model's tool call by reason
The synthetic row from connection.request and the tool.start row carried
different ids and no shared match value (op_id is not in the model's args),
so the card mounted twice. reason is the arg both sides carry.
* docs: manage_connections covers local MCP servers; connections.wait_timeout_seconds
* fix(connections): settle reason derives from target state, never from the renderer
A card that answers one of two targets and claims all_resolved must settle as
continue with the other target not_connected; found live with a two-target call.
* fix(desktop): a pending connection card re-arms on resume and activate
The store entry was restored but the transcript row was not, so navigating
away and back (or reloading) lost the card while the backend kept waiting.
restorePendingClarifyToolCall's core is generalized to any blocking tool
name and both resume paths project the connection row through it.
Verified live: card restored after navigate-away and after a full renderer
reload, deadline_at unchanged, approve settles connected.
* style: literal wording in added comments, docstrings and docs
* fix: shared gateway-event contract and config-schema category for the connection events
connection.request/expire replace mcp.setup.* in apps/shared gateway-events
(json list, BACKEND_EVENT_NAMES, GatewayEventMap) so the renderer's event
union includes them and the tui_gateway contract test passes. The new
`connections` config section folds into the agent tab like the other
single-field sections.
* style: import order (perfectionist) in the desktop and shared files this PR touches
* chore: retrigger CI (zero-job dispatch failure, auto-heal)
|
||
|
Teknium
|
3304d205be |
feat(video-gen): Kling 3.0 Standard + Pro families on the FAL backend
Adds kling-v3 (fal-ai/kling-video/v3/standard/*) and kling-v3-pro (fal-ai/kling-video/v3/pro/*) to FAL_FAMILIES: start_image_url i2v key, aspect_ratio dropped on i2v, string duration 3-15s, generate_audio and negative_prompt real, no seed/resolution keys per the published llms.txt schemas. Payload shapes pinned in tests; docs mention updated. |
||
|
teknium1
|
819988acb7 | docs(kanban): per-platform opt-in is the documented path (hermes tools enable kanban --platform X) | ||
|
Teknium
|
245e48008f |
fix: listing surfaces show the merged view for MCP servers named like built-in toolsets
get_all_toolsets() copied static TOOLSETS entries verbatim, so /toolsets and the dashboard showed only the built-in tools for a colliding name even though get_toolset() now unions the MCP alias in. Route those names through get_toolset() and document the alias/collision behaviour. |
||
|
Brooklyn Nicholson
|
c57581cd0d |
feat(tools): drive_preview and annotate_preview — the agent can use the page it opened
The in-app browser was a one-way mirror. open_preview put a page in the pane
and read_preview read its text back, but nothing could touch it. A click meant
falling back to the browser_* tools, which drive a separate Chromium the user
cannot see — so "log into this and pull my invoices" happened in a different
browser from the one on screen, with none of the sessions the user is already
signed into.
Four pieces, and they only make sense together:
· an in-page engine that inventories what is interactable and performs the
verb, injected as source because it has to run inside the guest page;
· the preview.act.request bridge from the gateway into the pane;
· drive_preview, for acting: elements, click, type, scroll, press, and the
pane's own back/forward/reload;
· annotate_preview, for marking without acting.
Those last two started as one tool doing two unrelated jobs. Leaving a mark is
not an action — it outlives the turn that drew it — so it gets its own verb,
and the interaction verb gets a name that says what it does.
Gating is the existing surface rule: desktop_ui folds in on session
source: 'desktop', and the bridge refuses to act for a background session, so a
turn running behind the user's back cannot reach into the page they are working
in.
Two details worth a reviewer's attention. Typing assigns through the
prototype's value setter, because React shadows value with its own accessor and
ignores an input event whose value it believes it already wrote — a plain
el.value = … types into a field that snaps back on the next render. And
clicking replays the pointer/mouse pair before activation, because frameworks
bind to mousedown as often as to click.
|
||
|
Brooklyn Nicholson
|
60e9ed12c4 |
feat(tools): close_preview so the agent can dismiss the pane it opened
open_preview and read_preview could drive the page, but nothing could close the pane. Same desktop_ui / session-source gate as the rest of the GUI tools. |
||
|
Brooklyn Nicholson
|
93b50ea0bb |
test+docs(tour): cover the engine and document the API
Ten behavior tests for target discovery, stable-selector ordering, step paging, recovery hints, and the self-containment contract the preview injection depends on. Docs cover data-tour markup and the curated-tour entry point alongside the tool itself. |
||
|
Jakub Wolniewiczandkaishi00
|
ae23b1f676 |
fix: complete kanban review lifecycle
Close the autonomous implement-review-rework loop, preserve parent gating and implementer provenance, distinguish downstream review cards, and surface legacy review dependency deadlocks immediately. Co-authored-by: kaishi00 <6590895+kaishi00@users.noreply.github.com> |
||
|
Nikita Barkov
|
16accefd2f |
feat(kanban): add first-class "review" handoff lifecycle
Add a non-terminal "review" status so a worker that finished implementation can hand off for human review without abusing kanban_block. The old kanban_block(reason="review-required: ...") convention routed the handoff through the unblock-loop breaker, so a normal review -> changes -> review cycle was falsely escalated to triage. - kanban_db: request_review (running/ready -> review, non-block, emits review_requested), reopen_review_task (review -> ready/todo, review_reopened), complete_task accepts review -> done, and a review_dispatch gate (default off, shared by the dispatcher loop and the gateway health probe). - kanban_request_review worker tool + `request-review` / `reopen-review` CLI verbs; tool wired through toolsets, EXPOSED_TOOLS, _POLISHED_TOOLS. - Gateway notifier wakes the origin subscriber on review_requested and block_loop_detected; the subscription survives until done/archived, so every review cycle re-notifies. - Dashboard PATCH + bulk route the review transitions (request_review / reopen_review_task) and render the review column. - goals.py goal-loop and KANBAN_GUIDANCE recognize review as a terminator. - Docs (reference tables, user guide, AGENTS.md, zh-Hans mirrors) + tests. needs_input / failed are unchanged: they still route through kanban_block, still count toward block_recurrences, and still escalate to triage. |
||
|
Brooklyn Nicholson
|
0c2cdccccc |
fix(build): win32 get-windows staging must skip the tarball's bundled darwin binding
The published tarball ships lib/binding/napi-9-darwin-unknown-arm64 on every platform, so a real Windows host has both it and the downloaded win32 binding — the classify-everything gate threw on the darwin dir and killed every Windows pack. Stage only bindings naming the target platform (classify still rejects impostors), stop copyGlobByExt from recursing into lib/binding, and add a version tripwire so a get-windows bump fails the build until the lib/windows.js rewrite is re-verified. Also from review: the renderer answers window.read.respond with empty text when the IPC invoke rejects (older shell / main-side throw) instead of stalling the tool's 30s timeout; the tool schema discloses that sibling Hermes windows are skipped; docs gain read_window_below in both references. |
||
|
Brooklyn Nicholson
|
f88f6f8e67 |
docs(reference): document the desktop_ui toolset
The six GUI tools moved out of `terminal` into their own toolset; the tables still described them as check_fn-gated members of it, and as available to every hermes-* platform bundle. |
||
|
brooklyn!
|
64646dda56 |
Hermes can read the in-app browser (#79482)
* feat(agent): read_preview — the desktop-gated tool that reads the in-app browser The agent could open the preview pane (open_preview) and read the embedded terminal (read_terminal), but the browser it had just opened was a black box — 'what does this page say?' had no answer. read_preview mirrors read_terminal end to end: HERMES_DESKTOP-gated via check_fn (zero schema footprint outside the GUI), dispatched through the same agent callback pattern, windowed with start/count so a long page pages instead of flooding context. * feat(gateway): preview.read blocking bridge Same lifecycle as terminal.read: the tool blocks on preview.read.request, the renderer answers preview.read.respond (allow_expired — a slow page extraction losing the 45s race must not surface a raw 4009), and a timeout emits preview.read.expire so late answers resolve quietly. * feat(desktop): the renderer serializes the active preview tab for the agent preview-reader.ts is the preview analog of the terminal's buffer registry: the URL pane registers a page reader (webview executeJavaScript → title + visible innerText) keyed by tab id; readActivePreview resolves the ACTIVE tab, windows the text (24k cap per read), and answers file/artifact tabs with identity plus a note pointing at the tool that reads that content directly. The gateway event handler answers preview.read.request beside terminal.read.request. |
||
|
Teknium
|
43874d1a96 |
docs: accuracy sweep + coverage for 2 months of shipped features
Accuracy pass (all 373 pages audited against code, 13 parallel audits):
- configuration.md: 12 stale defaults/keys (file-sync rewrite, clarify
timeout, streaming knobs, iteration budget, TTS/STT enums)
- reference/: commands/env-vars/toolsets/tools synced with
COMMAND_REGISTRY, argparse tree, OPTIONAL_ENV_VARS, TOOLSETS
(28 env vars added, 3 phantom removed, mcp__ naming, webhook
platform restricted toolset)
- features/, messaging/, developer-guide/, guides/: ~60 factual fixes
(web_extract truncation, dashboard auth fail-closed, delegation
blocked tools, adapter signatures, session schema v23, phantom
Matrix env vars, hermes setup tts, auth spotify, webhook --skills)
- zh-Hans: explicit heading IDs fix 2 broken WSL2 anchors
New coverage for features shipped in the last 2 months (verified
against code before writing):
- compression.in_place, verify-on-stop (+v31/v32 migration reality),
${env:VAR} SecretRef, display.timestamp_format, session:compress
hook + thread_id/chat_type fields
- /journey learning timeline, per-channel model/system-prompt
overrides, /sessions search, clarify multi-select, -z --usage-file,
uninstall --dry-run, config get/unset
- MCP elicitation, extra_headers, discover_models, api-server run cap,
Bedrock cachePoint, Discord reasoning_style, Google Chat clarify
cards, vibe reactions, resume cwd restore, Yuanbao forwarded
messages, api_content sidecar, roaming pet, tool_progress log mode,
WhatsApp polls/locations, kanban per-task model + lifecycle hooks
|
||
|
Julien Talbot
|
b9b100da11 |
docs(xai): clarify x_search vs xurl routing without schema cross-refs
Make the x_search / xurl boundary explicit in the skill, feature docs, toolset metadata, setup note, and reference pages, while keeping the model-facing x_search schema generic (no static xurl name). Regression tests assert behavioral routing invariants rather than frozen prose snapshots. Drop the stale CI-only plugin/hangup hunks already on main so this rebases cleanly. |
||
|
trkim
|
47bbc12e18 | fix(kanban): isolate delegated children from parent task | ||
|
Teknium
|
b31b0b9d95 |
docs: reconcile docs with code across last 3 releases (#54254)
Audited the last 3 releases (v2026.5.28..main) against the docs site and fixed code-vs-docs drift: - slash-commands: add /moa, /prompt, /pet, /hatch, /timestamps - cli-commands: add hermes pets / project / desktop / whatsapp-cloud + dashboard register; correct --insecure (now a deprecated no-op); add gateway migrate-legacy + enroll --wake-url + dashboard --skip-build - environment-variables: document the remaining ~48 env vars (SimpleX, Photon, Teams adapter, per-platform *_ALLOW_ALL_USERS, home-channel vars, IRC, Brave/Krea/Notion/Linear/Airtable/Tenor keys, QQ_SANDBOX) — full OPTIONAL_ENV_VARS (265) now covered - configuration: document tool_loop_guardrails, goals, prompt_caching, network, onboarding, dashboard config blocks - toolsets/tools-reference + tools.md: add coding/project toolsets and read_terminal/project_* tools; remove the stale messaging toolset and send_message agent tool (removed in #47856); drop stale RL-training prose - messaging: new IRC channel page (adapter shipped without docs) + index row + sidebar + env vars - pets: document the /hatch AI generation pipeline + Nous/OpenRouter image backend - web-dashboard: document the bearer-token / TokenPrincipal service auth path - purge agent-callable send_message references across guides/features and the research-paper-writing skill (tool removed in #47856) Verified: docusaurus build succeeds; all authored internal links resolve. |
||
|
ethernet
|
772cf847b0 | feat(docs): clarify platform support | ||
|
Teknium
|
c6575df927 |
feat(moa): expose MoA presets as selectable virtual models (#46081)
* feat(moa): expose MoA presets as selectable virtual models Reconstructed onto current main (PR #46081's base had diverged with no common ancestor, marking the PR dirty so CI never dispatched). MoA is now a virtual provider: each named preset is a selectable model under provider 'moa', and the preset's aggregator is the acting model that answers and calls tools. Reference models fan out in parallel via a bounded ThreadPoolExecutor (the same batch pattern delegate_task uses) — all references dispatched at once, collected when every one finishes, then handed to the aggregator. Output order is preserved, failures and the MoA-recursion guard stay isolated per reference. - Removed the old mixture_of_agents model tool and moa toolset. - Added moa as a virtual provider in the provider/model inventory. - /moa is shortcut behavior over model selection (default preset / named preset / one-shot prompt). - Dashboard + Desktop manage named presets; presets appear in model pickers. - Parallel reference fan-out in agent/moa_loop.py with regression test. * fix(moa): thread moa_config through _run_agent to _run_agent_inner The reconstructed gateway MoA wiring declared moa_config on _run_agent (the profile-scoping wrapper) and used it inside _run_agent_inner, but the wrapper never forwarded it — _run_agent_inner had no such parameter, so the runtime hit NameError: name 'moa_config' is not defined on the compression-failure session sync path. Add moa_config to _run_agent_inner's signature and forward it from both wrapper call sites (multiplex and non-multiplex). Caught by tests/gateway/test_compression_failure_session_sync.py on CI shard test(4). * fix(moa): classify moa as a virtual provider in the catalog The moa virtual provider has no PROVIDER_REGISTRY/ProviderProfile entry, so provider_catalog() fell through to the default auth_type="api_key" with no env vars — tripping two catalog invariants: - test_provider_catalog: api_key providers must expose a credential env var - test_provider_parity: every hermes-model provider must be desktop-configurable moa already declares auth_type="virtual" in HERMES_OVERLAYS; consult that overlay as an auth_type fallback so the catalog reports moa as virtual (no real credential, no network endpoint). Exempt virtual providers from the desktop parity union check the same way 'custom' is exempt — derived from the catalog, not a hardcoded slug, so future virtual providers are covered too. |
||
|
Teknium
|
2d099fed1e |
docs: deep audit — registry drift, stale claims, 2-week PR coverage, dashboard screenshot (#40952)
Full-corpus correctness audit of the hand-written docs against the codebase, plus a 2-week merged-PR coverage sweep and one live dashboard screenshot. Correctness (verified against COMMAND_REGISTRY / PROVIDER_REGISTRY / TOOLSETS / tools.registry / DEFAULT_CONFIG / source): - reference: add /version slash command, context_engine toolset, openai-api + novita-ai to --provider; fix tool count 64->71; model_catalog ttl 24->1; add profile describe to summary table; add real provider env vars (LM_API_KEY/LM_BASE_URL, KIMI_CODING_API_KEY, ALIBABA_CODING_PLAN_*, ANTHROPIC_BASE_URL, COPILOT_API_BASE_URL); fix faq "Windows: not natively". - user-guide: fix broken `hermes -w -q` (->-z) and `hermes logs --tail` (->-f); language list 8->16; aux slots 8->11; docker separate-dashboard claim; _SECURITY_ARGS -> _BASE_SECURITY_ARGS. - features: curator prune_builtins truth + missing CLI verbs; codex-runtime aux keys (context_compression->compression, vision_detect->vision); kanban terminate endpoint + promote/reassign/schedule/diagnostics/edit + per-profile cap; mcp mTLS (client_cert/client_key); built-in-plugins nemo_relay + teams_pipeline; api-server run approval endpoint; computer-use frontmatter. - features N-Z + integrations: StepFun step-3-mini->step-3.5-flash; web-search backends 4->8; tool-gateway image-model IDs; voice-mode STT/TTS enums; remove phantom `rl` toolset; nous-portal status subcommand. - messaging: WeCom typing/streaming cols; telegram transport default edit->auto; sms host default; simplex/ntfy `gateway setup` + pairing approve; line smart-chunking; matrix MATRIX_DM_AUTO_THREAD. - developer-guide: build-a-plugin code examples (register_command signature, ContextEngine/ImageGenProvider/MemoryProvider ABCs); model-provider-plugin entry-point group hermes.plugins->hermes_agent.plugins; PLUGIN.yaml->plugin.yaml; agent-loop stale LOC; web-search-provider phantom crawl(). PR coverage (2-week window, 149 feat PRs): - desktop.md refreshed for ~15 shipped features (zh-Hans switcher, rebindable shortcuts + zoom + Cmd+K, status-bar model picker + YOLO toggle, session-by-id + archive, multi-profile concurrent + cross-profile @session, composer history, Providers pane, per-profile remote hosts, Grok OAuth, aux-pin warning). - configuration.md gateway-streaming default corrected to per-platform. - tool-gateway.md free tool pool entitlement note. Media: - New /img/dashboard/admin-config.png — live dashboard Config admin page (captured from a clean profile, no secrets/personalization). |
||
|
Teknium
|
d276018378 |
docs(toolsets): clarify all/* wildcard does not enable kanban (#35729)
The all/* wildcard expands to every registered toolset, but a handful of tools have an additional check_fn gate on top of toolset membership and are intentionally NOT turned on by all/* alone: - Capability-gated tools (browser, computer_use, code_execution, Feishu, Home Assistant, cronjob) require their backend/credential prerequisite. - The kanban toolset is workflow-gated and deliberately opt-in. Kanban tools mutate shared board state, so they stay off by default even under all/* — you must list 'kanban' by name (or be a dispatcher-spawned worker with HERMES_KANBAN_TASK set). This was the expectations gap behind #35581 — the docs previously said all/* expands to 'every registered toolset' without noting the carve-out. Closes #35581. |
||
|
bensargotest-sys
|
81584940fe |
docs: align kanban readiness docs and smoke tests
Salvages #28199 by @bensargotest-sys. Aligns Kanban docs with current tool registration: dispatcher-spawned task workers get task tools, profiles that explicitly enable the kanban toolset get orchestrator routing tools (kanban_list, kanban_unblock). Corrects failure-limit text to current default of 2. Hardens the e2e subprocess script to resolve repo root and use the spawnable default assignee. Updates the diagnostics severity fixture to assert error below the critical threshold. |
||
|
TekniumandJaaneek
|
74d0b392e7 |
feat(x_search): gated X (Twitter) search tool with OAuth-or-API-key auth (#26763)
* feat(x_search): gated X (Twitter) search tool with OAuth-or-API-key auth Salvages tools/x_search_tool.py from the closed PR #10786 (originally by @Jaaneek) and reworks its credential resolution so the tool registers when EITHER xAI credential path is available: * XAI_API_KEY (paid xAI API key) is set in ~/.hermes/.env or the env, OR * The user is signed in via xAI Grok OAuth — SuperGrok subscription — i.e. hermes auth add xai-oauth has been run Both paths route through xAI's built-in x_search Responses tool at https://api.x.ai/v1/responses. When both credentials exist OAuth wins, matching tools/xai_http.py's existing preference order (uses SuperGrok quota instead of paid API spend). The check_fn calls resolve_xai_http_credentials() which auto-refreshes the OAuth access token if it's within the refresh skew window, so a True return means the bearer is fetchable AND non-empty. Wiring - tools/x_search_tool.py — new tool, ~370 LOC. Schema gated by check_fn, bearer resolved per-call so revoked OAuth surfaces a clean tool_error rather than an HTTP 401. - toolsets.py — "x_search" toolset def. NOT added to _HERMES_CORE_TOOLS; users opt in via hermes tools. - hermes_cli/tools_config.py — CONFIGURABLE_TOOLSETS entry + TOOL_CATEGORIES block with two provider options (OAuth + API key) sharing the existing xai_grok post_setup hook for credential bootstrap. - hermes_cli/config.py — DEFAULT_CONFIG["x_search"] with model / timeout_seconds / retries. Additive nested key; no version bump. - tests/tools/test_x_search_tool.py — 13 tests covering HTTP shape, handle validation, citation extraction, 4xx/5xx/timeout handling, and the full credential-resolution matrix (OAuth-only, API-key-only, both-set, neither-set, resolver-raises, config overrides, registry registration). - website/docs/guides/xai-grok-oauth.md — adds X Search to the direct-to-xAI tools section with off-by-default note. - website/docs/user-guide/features/tools.md — new row in the tools table. Off by default — users enable via `hermes tools` → 🐦 X (Twitter) Search. Schema only appears to the model when xAI credentials are configured. Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> * docs(x_search): add dedicated feature page + reference entries - website/docs/user-guide/features/x-search.md (new) — full feature walkthrough: authentication, enablement, configuration, parameters, returned fields, example, troubleshooting, see-also links. - website/docs/reference/tools-reference.md — new "x_search" toolset section with parameter docs and credential gating note. - website/docs/reference/toolsets-reference.md — new row in the toolset catalog table. - website/sidebars.ts — wires the new feature page under Media & Web, after web-search. --------- Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> |
||
|
Siddharth Balyan
|
5af672c753 |
chore: remove Atropos RL environments and tinker-atropos integration (#26106)
* chore: remove Atropos RL environments, tools, tests, skill, and tinker-atropos submodule Delete: - environments/ (43 files — base env, agent loop, tool call parsers, benchmarks) - rl_cli.py (standalone RL training CLI) - tools/rl_training_tool.py (all 10 rl_* tools) - tests: test_rl_training_tool, test_tool_call_parsers, test_managed_server_tool_support, test_agent_loop, test_agent_loop_vllm, test_agent_loop_tool_calling, test_terminalbench2_env_security - optional-skills/mlops/hermes-atropos-environments/ - tinker-atropos git submodule + .gitmodules * chore: remove RL/Atropos references from Python source - toolsets.py: remove rl toolset block + update comment - model_tools.py: remove rl_tools group + update async bridging comment - hermes_cli/tools_config.py: remove RL display entry, _DEFAULT_OFF_TOOLSETS, setup block, and rl_training post-setup handler - tools/budget_config.py: remove RL environment reference in docstring - tests/test_model_tools.py: remove rl_tools from expected groups - tests/run_agent/test_streaming_tool_call_repair.py: fix stale cross-reference * chore: remove rl/yc-bench extras and tinker-atropos refs from pyproject.toml - Remove rl extra (atroposlib, tinker, fastapi, uvicorn, wandb) - Remove yc-bench extra - Remove rl_cli from py-modules - Remove [tool.ty.src] exclude for tinker-atropos - Remove [tool.ruff] exclude for tinker-atropos - Regenerate uv.lock * chore: remove tinker-atropos from install/setup scripts - setup-hermes.sh: remove entire tinker-atropos submodule install block - scripts/install.sh: remove both tinker-atropos blocks (Termux + standard) - scripts/install.ps1: remove tinker-atropos block - nix/hermes-agent.nix: remove tinker-atropos pip install line * chore: remove RL references from cli-config.yaml.example * docs: remove Atropos/RL references from README, CONTRIBUTING, AGENTS.md * docs: remove RL/Atropos references from website - Delete: environments.md, rl-training.md, mlops-hermes-atropos-environments.md - sidebars.ts: remove rl-training and environments sidebar entries - optional-skills-catalog.md: remove hermes-atropos-environments row - tools-reference.md: remove entire rl toolset section - toolsets-reference.md: remove rl row + update example - integrations/index.md: remove RL Training bullet - architecture.md: remove environments/ from tree + RL section - contributing.md: remove tinker-atropos setup - updating.md: remove tinker-atropos install + stale submodule update * chore: remove remaining RL/Atropos stragglers - hermes_cli/config.py: remove TINKER_API_KEY + WANDB_API_KEY env var defs - hermes_cli/doctor.py: remove Submodules check section (tinker-atropos) - hermes_cli/setup.py: remove RL Training status check - hermes_cli/status.py: remove Tinker + WandB from API key status display - agent/display.py: remove both rl_* tool preview/activity blocks - website/docs: remove RL references from providers.md + env-variables.md - tests: remove TINKER_API_KEY from conftest, set_config_value, setup_script * chore: remove RL training section from .env.example |
||
|
TekniumandJaaneek
|
9d42c2c286 |
feat(video_gen): unified video_generate tool with pluggable provider backends (#25126)
* feat(video_gen): unified video_generate tool with pluggable provider backends One core video_generate tool, every backend a plugin. Mirrors the image_gen + memory_provider + context_engine architecture: ABC, registry, plugin-context registration hook, and per-plugin model catalogs surfaced through hermes tools. Surface (one schema, every backend): - operation: generate / edit / extend - modalities: text-to-video (prompt only), image-to-video (prompt + image_url), video edit (prompt + video_url), video extend (video_url) - reference_image_urls, duration, aspect_ratio, resolution, negative_prompt, audio, seed, model override - Providers ignore unknown kwargs and declare what they support via VideoGenProvider.capabilities() — backend-specific quirks stay in the backend, the agent learns one tool Backends shipped: - plugins/video_gen/xai/ — Grok-Imagine, full generate/edit/extend + image-to-video + reference images (salvaged from PR #10600 by @Jaaneek, reshaped into the plugin interface) - plugins/video_gen/fal/ — Veo 3.1 (t2v + i2v), Kling O3 i2v, Pixverse v6 i2v with model-aware payload building that drops keys a model doesn't declare Wiring: - agent/video_gen_provider.py — VideoGenProvider ABC, normalize_operation, success_response / error_response, save_b64_video / save_bytes_video, $HERMES_HOME/cache/videos/ - agent/video_gen_registry.py — thread-safe register/get/list + get_active_provider() reading video_gen.provider from config.yaml - hermes_cli/plugins.py — PluginContext.register_video_gen_provider() - hermes_cli/tools_config.py — Video Generation category in hermes tools, plugin-only providers list, model picker per plugin, config write to video_gen.{provider,model} - toolsets.py — new video_gen toolset - tests: 31 new tests covering ABC, registry, tool dispatch, both plugins - docs: developer-guide/video-gen-provider-plugin.md (parallel to the image-gen guide), sidebar + toolsets-reference + plugin guides updated Supersedes: #25035 (FAL), #17972 (FAL), #14543 (xAI), #13847 (HappyHorse), #10458 (provider categories), #10786 (xAI media+search bundle), #2984 (FAL duplicate), #19086 (Google Veo standalone — easy port to plugin interface). Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> * feat(video_gen): dynamic schema reflects active backend's capabilities Address the 'capability variance' question — instead of one tool with a static schema that lies about what every backend supports, the video_generate tool now rebuilds its description at get_definitions() time based on the configured video_gen.provider and video_gen.model. The agent sees backend-specific guidance up-front: - 'fal-ai/veo3.1/image-to-video': 'image-to-video only — image_url is REQUIRED; text-only prompts will be rejected' - 'fal-ai/veo3.1' (t2v): no image_url restriction shown - xAI grok-imagine-video: 'operations: generate, edit, extend; up to 7 reference_image_urls' - Backends without edit/extend: 'not supported on this backend — surface that they need to switch backends via hermes tools' This is the same pattern PR #22694 used for delegate_task self-capping — documented in the dynamic-tool-schemas skill. Cache invalidation is free: get_tool_definitions() already memoizes on config.yaml mtime, so a mid-session backend swap rebuilds the schema automatically. Tested: - Empirical FAL OpenAPI schema check confirms image-to-video models require image_url (FAL returns HTTP 422 otherwise) — client-side rejection in FALVideoGenProvider.generate() now prevents the wasted round-trip - Live E2E: fal-ai/veo3.1/image-to-video + prompt-only → clean missing_image_url error; fal-ai/veo3.1 + prompt-only → dispatches - 6 new tests cover the builder (no config / image-only / full-surface / text-only / unknown provider / registry wiring), all passing - 37/37 in the slice, 134/134 in the broader regression set * test(video_gen/xai): full surface integration tests + cleaner schema Verified end-to-end that the xAI plugin handles every documented mode from PR #10600's surface: text-to-video, image-to-video, reference-images-to-video, video edit, video extend (with and without prompt). All five modes route to the correct xAI endpoint (/videos/generations, /videos/edits, /videos/extensions) with the right payload shape (image / reference_images / video keys), and all five client-side rejections fire before the network: edit-without-prompt, extend-without-video_url, image+refs conflict, >7 references, and duration/aspect_ratio clamping. 15 new integration tests grouped into four classes (endpoint routing, modalities, validation, clamping). httpx is stubbed via a small fake AsyncClient that records POSTs so the tests assert the actual payload the plugin would send to xAI — not just the success/error envelope. Also cleaned up a description redundancy: when a model's operations match the backend's overall set, we no longer print the duplicate 'operations supported by this model' line. xAI's description now reads: Active backend: xAI . model: grok-imagine-video - operations supported by this backend: edit, extend, generate - modalities supported by this backend: image, reference_images, text - aspect_ratio choices: 16:9, 1:1, 2:3, 3:2, 3:4, 4:3, 9:16 - resolution choices: 480p, 720p - duration range: 1-15s - reference_image_urls: up to 7 images Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> * feat(video_gen): collapse surface to t2v + i2v, family-based auto-routing Two design changes per Teknium: 1) Drop edit/extend from the tool surface entirely. Only text-to-video and image-to-video remain. The agent sees a clean tool with two modalities; backend-specific quirks like xAI's edit/extend endpoints stay out of the unified schema. 2) FAL: pick a model FAMILY once, the plugin routes between the family's text-to-video and image-to-video endpoints based on whether image_url was passed. Users no longer pick 'fal-ai/veo3.1' AND 'fal-ai/veo3.1/image-to-video' as separate options — they pick 'veo3.1', and the plugin handles the rest. Catalog rewritten as families: veo3.1 fal-ai/veo3.1 / fal-ai/veo3.1/image-to-video pixverse-v6 fal-ai/pixverse/v6/text-to-video / fal-ai/pixverse/v6/image-to-video kling-o3-standard fal-ai/kling-video/o3/standard/text-to-video / fal-ai/kling-video/o3/standard/image-to-video xAI uses a single endpoint (/videos/generations) for both modes, routed by the presence of the 'image' field in the payload — no edit/extend exposure. Schema changes: - VIDEO_GENERATE_SCHEMA: drop operation, drop video_url. Final params: prompt (required), image_url, reference_image_urls, duration, aspect_ratio, resolution, negative_prompt, audio, seed, model. - VideoGenProvider ABC: drop normalize_operation, VALID_OPERATIONS, DEFAULT_OPERATION. capabilities() drops 'operations' key. - success_response: add 'modality' field ('text' | 'image') so the agent and logs can see which endpoint was actually hit. Dynamic schema builder simplified — no operations bullet, no 'switch backends if you need edit/extend' guidance. When the active backend supports both modalities (the common case), description reads: Active backend: FAL . model: pixverse-v6 - supports both text-to-video (omit image_url) and image-to-video (pass image_url) - routes automatically - aspect_ratio choices: 16:9, 9:16, 1:1 - resolution choices: 360p, 540p, 720p, 1080p - duration range: 1-15s - audio: pass audio=true to enable native audio (pricing tier) - negative_prompt: supported Tests: 51 in the video_gen slice, 216 across the broader image+video sweep, all passing. New FAL routing tests prove pixverse-v6 + no image hits text-to-video endpoint, pixverse-v6 + image_url hits image-to-video endpoint, same for veo3.1 and kling-o3-standard. Docs updated: developer-guide page rewrites the 'model families' pattern as a first-class section so external plugin authors know the convention. toolsets-reference and toolsets.py descriptions match the new surface. Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> * feat(video_gen/fal): expand catalog to 6 families, cheap + premium tiers Catalog now covers everything Teknium specced from FAL: Cheap tier: ltx-2.3 fal-ai/ltx-2.3-22b/text-to-video / image-to-video pixverse-v6 fal-ai/pixverse/v6/text-to-video / image-to-video Premium tier: veo3.1 fal-ai/veo3.1 / fal-ai/veo3.1/image-to-video seedance-2.0 bytedance/seedance-2.0/text-to-video / image-to-video kling-v3-4k fal-ai/kling-video/v3/4k/text-to-video / image-to-video happy-horse fal-ai/happy-horse/text-to-video / image-to-video DEFAULT_MODEL moved from veo3.1 (premium) to pixverse-v6 (cheap, sane defaults, both modalities) — better first-run UX for users who haven't explicitly picked a model. New family-entry knob: image_param_key. Kling v3 4K's image-to-video endpoint expects start_image_url instead of image_url; declaring image_param_key='start_image_url' on the family lets _build_payload remap correctly. Other families default to plain image_url. Per-family capability flags reflect each model's docs: - LTX 2.3 + Happy Horse: minimal payloads (no duration/aspect/resolution enum exposed by FAL — let endpoint apply defaults) - Seedance: 6 aspect ratios incl 21:9, durations 4-15, audio supported, negative prompts NOT supported per docs - Kling v3 4K: 16:9/9:16/1:1, 3-15s, audio + negative - Veo 3.1: unchanged, 16:9/9:16, 4/6/8s Tests: +5 covering the new families (full catalog, Kling 4K start_image_url remap, Seedance routing, LTX payload minimality, Happy Horse minimality). 56/56 in the slice green. Note: I did NOT add the FAL-hosted xAI Grok-Imagine variant. Hermes already has a direct xAI plugin that talks to xAI's own API; routing the same model through FAL's wrapper would duplicate the surface without adding capabilities. Users on FAL who want Grok-Imagine should use the xAI plugin directly; flag if you want both routes available. * test(video_gen): tool-surface routing matrix — every model x modality End-to-end matrix test driven through _handle_video_generate() — the actual function the agent's video_generate tool call lands in. Writes config.yaml, invokes the registered handler with a raw args dict, then asserts the outbound HTTP/SDK call hit the right endpoint with the right payload shape. Parametrized over FAL_FAMILIES.keys() so the matrix auto-discovers new families as they're added (add a family to FAL_FAMILIES and you get both modalities tested for free). Coverage: - All 6 FAL families x {text-only, text+image} = 12 cases - xAI x {text-only, text+image} = 2 cases - tool-level model= arg overrides config = 2 cases For each case, verifies: - result['success'] is True - result['modality'] matches input shape ('text' if no image_url, 'image' otherwise) - outbound endpoint URL matches the family's text_endpoint or image_endpoint - text-only payloads carry no image-shaped keys - text+image payloads carry the family's image key (image_url for most, start_image_url for kling-v3-4k, wrapped 'image' object for xAI) All 16 cases passing. Confirms the tool surface routes every (provider, model, modality) combination correctly with zero leakage. * feat(video_gen): keep video_gen out of first-run setup, surface in status Two changes: 1. video_gen joins _DEFAULT_OFF_TOOLSETS, so it is NOT pre-selected in the first-run toolset checklist. Video gen is niche, paid, and slow — most users don't want it nagging them during initial setup. Anyone who wants it opts in via 'hermes tools' -> Video Generation, which already routes to the provider+model picker. 2. The 'hermes setup' status panel learns about video_gen — but only shows the row when a plugin reports available. Users without FAL_KEY/XAI_API_KEY see nothing about video gen; users with one of those keys see 'Video Generation (FAL) ✓' as confirmation it's wired. Verified live: - Fresh install (no creds): zero video_gen mentions in wizard. - With FAL_KEY: status row appears with active backend name. - 160/160 in the setup + tools_config + video_gen test slice. Rationale: image_gen is on by default because it's a featured creative tool used in casual chat (telegrams, etc). Video gen is heavier — long wait, paid per-second pricing. Default-off matches user intent better. --------- Co-authored-by: Jaaneek <Jaaneek@users.noreply.github.com> |
||
|
Teknium
|
252d68fd45 |
docs: deep audit — fix stale config keys, missing commands, and registry drift (#22784)
* docs: deep audit — fix stale config keys, missing commands, and registry drift Cross-checked ~80 high-impact docs pages (getting-started, reference, top-level user-guide, user-guide/features) against the live registries: hermes_cli/commands.py COMMAND_REGISTRY (slash commands) hermes_cli/auth.py PROVIDER_REGISTRY (providers) hermes_cli/config.py DEFAULT_CONFIG (config keys) toolsets.py TOOLSETS (toolsets) tools/registry.py get_all_tool_names() (tools) python -m hermes_cli.main <subcmd> --help (CLI args) reference/ - cli-commands.md: drop duplicate hermes fallback row + duplicate section, add stepfun/lmstudio to --provider enum, expand auth/mcp/curator subcommand lists to match --help output (status/logout/spotify, login, archive/prune/ list-archived). - slash-commands.md: add missing /sessions and /reload-skills entries + correct the cross-platform Notes line. - tools-reference.md: drop bogus '68 tools' headline, drop fictional 'browser-cdp toolset' (these tools live in 'browser' and are runtime-gated), add missing 'kanban' and 'video' toolset sections, fix MCP example to use the real mcp_<server>_<tool> prefix. - toolsets-reference.md: list browser_cdp/browser_dialog inside the 'browser' row, add missing 'kanban' and 'video' toolset rows, drop the stale '38 tools' count for hermes-cli. - profile-commands.md: add missing install/update/info subcommands, document fish completion. - environment-variables.md: dedupe GMI_API_KEY/GMI_BASE_URL rows (kept the one with the correct gmi-serving.com default). - faq.md: Anthropic/Google/OpenAI examples — direct providers exist (not just via OpenRouter), refresh the OpenAI model list. getting-started/ - installation.md: PortableGit (not MinGit) is what the Windows installer fetches; document the 32-bit MinGit fallback. - installation.md / termux.md: installer prefers .[termux-all] then falls back to .[termux]. - nix-setup.md: Python 3.12 (not 3.11), Node.js 22 (not 20); fix invalid 'nix flake update --flake' invocation. - updating.md: 'hermes backup restore --state pre-update' doesn't exist — point at the snapshot/quick-snapshot flow; correct config key 'updates.pre_update_backup' (was 'update.backup'). user-guide/ - configuration.md: api_max_retries default 3 (not 2); display.runtime_footer is the real key (not display.runtime_metadata_footer); checkpoints defaults enabled=false / max_snapshots=20 (not true / 50). - configuring-models.md: 'hermes model list' / 'hermes model set ...' don't exist — hermes model is interactive only. - tui.md: busy_indicator -> tui_status_indicator with values kaomoji|emoji|unicode|ascii (not kawaii|minimal|dots|wings|none). - security.md: SSH backend keys (TERMINAL_SSH_HOST/USER/KEY) live in .env, not config.yaml. - windows-wsl-quickstart.md: there is no 'hermes api' subcommand — the OpenAI-compatible API server runs inside hermes gateway. user-guide/features/ - computer-use.md: approvals.mode (not security.approval_level); fix broken ./browser-use.md link to ./browser.md. - fallback-providers.md: top-level fallback_providers (not model.fallback_providers); the picker is subcommand-based, not modal. - api-server.md: API_SERVER_* are env vars — write to per-profile .env, not 'hermes config set' which targets YAML. - web-search.md: drop web_crawl as a registered tool (it isn't); deep-crawl modes are exposed through web_extract. - kanban.md: failure_limit default is 2, not '~5'. - plugins.md: drop hard-coded '33 providers' count. - honcho.md: fix unclosed quote in echo HONCHO_API_KEY snippet; document that 'hermes honcho' subcommand is gated on memory.provider=honcho; reconcile subcommand list with actual --help output. - memory-providers.md: legacy 'hermes honcho setup' redirect documented. Verified via 'npm run build' — site builds cleanly; broken-link count went from 149 to 146 (no regressions, fixed a few in passing). * docs: round 2 audit fixes + regenerate skill catalogs Follow-up to the previous commit on this branch: Round 2 manual fixes: - quickstart.md: KIMI_CODING_API_KEY mentioned alongside KIMI_API_KEY; voice-mode and ACP install commands rewritten — bare 'pip install ...' doesn't work for curl-installed setups (no pip on PATH, not in repo dir); replaced with 'cd ~/.hermes/hermes-agent && uv pip install -e ".[voice]"'. ACP already ships in [all] so the curl install includes it. - cli.md / configuration.md: 'auxiliary.compression.model' shown as 'google/gemini-3-flash-preview' (the doc's own claimed default); actual default is empty (= use main model). Reworded as 'leave empty (default) or pin a cheap model'. - built-in-plugins.md: added the bundled 'kanban/dashboard' plugin row that was missing from the table. Regenerated skill catalogs: - ran website/scripts/generate-skill-docs.py to refresh all 163 per-skill pages and both reference catalogs (skills-catalog.md, optional-skills-catalog.md). This adds the entries that were genuinely missing — productivity/teams-meeting-pipeline (bundled), optional/finance/* (entire category — 7 skills: 3-statement-model, comps-analysis, dcf-model, excel-author, lbo-model, merger-model, pptx-author), creative/hyperframes, creative/kanban-video-orchestrator, devops/watchers, productivity/shop-app, research/searxng-search, apple/macos-computer-use — and rewrites every other per-skill page from the current SKILL.md. Most diffs are tiny (one line of refreshed metadata). Validation: - 'npm run build' succeeded. - Broken-link count moved 146 -> 155 — the +9 are zh-Hans translation shells that lag every newly-added skill page (pre-existing pattern). No regressions on any en/ page. |
||
|
Teknium
|
850413f120 |
feat(computer-use): cua-driver backend, universal any-model schema
Background macOS desktop control via cua-driver MCP — does NOT steal the user's cursor or keyboard focus, works with any tool-capable model. Replaces the Anthropic-native `computer_20251124` approach from the abandoned #4562 with a generic OpenAI function-calling schema plus SOM (set-of-mark) captures so Claude, GPT, Gemini, and open models can all drive the desktop via numbered element indices. - `tools/computer_use/` package — swappable ComputerUseBackend ABC + CuaDriverBackend (stdio MCP client to trycua/cua's cua-driver binary). - Universal `computer_use` tool with one schema for all providers. Actions: capture (som/vision/ax), click, double_click, right_click, middle_click, drag, scroll, type, key, wait, list_apps, focus_app. - Multimodal tool-result envelope (`_multimodal=True`, OpenAI-style `content: [text, image_url]` parts) that flows through handle_function_call into the tool message. Anthropic adapter converts into native `tool_result` image blocks; OpenAI-compatible providers get the parts list directly. - Image eviction in convert_messages_to_anthropic: only the 3 most recent screenshots carry real image data; older ones become text placeholders to cap per-turn token cost. - Context compressor image pruning: old multimodal tool results have their image parts stripped instead of being skipped. - Image-aware token estimation: each image counts as a flat 1500 tokens instead of its base64 char length (~1MB would have registered as ~250K tokens before). - COMPUTER_USE_GUIDANCE system-prompt block — injected when the toolset is active. - Session DB persistence strips base64 from multimodal tool messages. - Trajectory saver normalises multimodal messages to text-only. - `hermes tools` post-setup installs cua-driver via the upstream script and prints permission-grant instructions. - CLI approval callback wired so destructive computer_use actions go through the same prompt_toolkit approval dialog as terminal commands. - Hard safety guards at the tool level: blocked type patterns (curl|bash, sudo rm -rf, fork bomb), blocked key combos (empty trash, force delete, lock screen, log out). - Skill `apple/macos-computer-use/SKILL.md` — universal (model-agnostic) workflow guide. - Docs: `user-guide/features/computer-use.md` plus reference catalog entries. 44 new tests in tests/tools/test_computer_use.py covering schema shape (universal, not Anthropic-native), dispatch routing, safety guards, multimodal envelope, Anthropic adapter conversion, screenshot eviction, context compressor pruning, image-aware token estimation, run_agent helpers, and universality guarantees. 469/469 pass across tests/tools/test_computer_use.py + the affected agent/ test suites. - `model_tools.py` provider-gating: the tool is available to every provider. Providers without multi-part tool message support will see text-only tool results (graceful degradation via `text_summary`). - Anthropic server-side `clear_tool_uses_20250919` — deferred; client-side eviction + compressor pruning cover the same cost ceiling without a beta header. - macOS only. cua-driver uses private SkyLight SPIs (SLEventPostToPid, SLPSPostEventRecordTo, _AXObserverAddNotificationAndCheckRemote) that can break on any macOS update. Pin with HERMES_CUA_DRIVER_VERSION. - Requires Accessibility + Screen Recording permissions — the post-setup prints the Settings path. Supersedes PR #4562 (pyautogui/Quartz foreground backend, Anthropic- native schema). Credit @0xbyt4 for the original #3816 groundwork whose context/eviction/token design is preserved here in generic form. |
||
|
Teknium
|
289cc47631 |
docs: resync reference, user-guide, developer-guide, and messaging pages against code (#17738)
Broad drift audit against origin/main (
|