A signed-in, paid Nous account that the portal had not enabled for
connectors got `manage_connections` in its schema and a raw "tool gateway
request failed with status 404" back from every call. The gateway answers
404 for any such account by design, and Hermes gated the tool on paid access
or a free tool pool, which says nothing about that.
The gate now reads the portal's own answer: a `managed_tools` token claim,
plus the existing free-tier leg. The gate is also the tool's check_fn, so a
session without the claim never sees the tool and the model has no 404 to
narrate. A token without the claim reads as not enabled.
* 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.
* 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)
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.
The salvaged #103267 plugin hardcoded a single model (minimax/hailuo-3-max) and
rejected any other id. OpenRouter's public GET /api/v1/videos/models already
publishes every generative model with its supported durations, resolutions,
aspect ratios, frame-image support, audio and seed flags, and pricing SKUs, so
the provider now reads that catalog (5-min TTL, offline snapshot fallback):
- list_models(): all 25+ generative models (edit/upscale/avatar rows that take
no duration are outside the unified video_generate surface and are dropped)
with a per-second price label where the SKU is per-second
- capabilities(): the CONFIGURED model's surface, so the dynamic schema only
advertises audio/seed/resolutions the selected model honours
- _build_payload(): clamps duration/resolution/aspect ratio to the model's
live limits (nearest by value/height/ratio) and drops generate_audio/seed
for models that lack them (the API 400s otherwise); reference images ride
in input_references; local file inputs are refused (OpenRouter fetches
URLs itself), data:image/ URLs from the sandbox chokepoint pass through
- bearer key only ever goes to the configured origin (poll + /content),
never to a provider-supplied unsigned_urls host (kept from #103267)
Also drops the source-grep `_IGNORES_SEED` escape hatch #103267 added to the
declaration⇄implementation sweep; the provider now implements seed for real.
Docs list OpenRouter and DeepInfra as bundled video backends.
Requested by Don Piedro Savastano (Discord): OpenRouter credit for video_generate.
The idle tip rotation walked the catalog as a ring: after the last tip it
wrapped to the first, so a user who had already seen every tip kept
getting "Start fresh", "Teach it once", ... again every six hours for as
long as they used the app. Only the X stopped a tip, and letting a bubble
time out (the normal way it leaves) counted for nothing.
The walk is now one lap. nextTip also steps over every tip in the seen
ledger ($tipShownAt, which already recorded every catalog tip that
reached the screen), so a tip shows once however it left, and the
rotation runs dry once every tip has had its moment. Settings > Reset
clears the seen ledger and the cursor as well as the retired set, and its
button counts what a Reset would actually bring back (shown or closed,
counted once). Agent tips carry no catalog id and are untouched.
Live repro (Playwright against the worktree's Vite renderer, all nine
tips seeded as seen, clock fast-forwarded past settle + cooldown):
origin/main re-showed "Start fresh"; fixed renderer shows nothing;
a fresh user (nothing seen) still gets the first tip.
Adds plugins/web/perplexity — a keyed-only WebSearchProvider over httpx:
- search: POST https://api.perplexity.ai/search (documented Search API),
search_context_size=low so `snippet` stays description-sized;
results[].snippet -> description, max_results capped at the API's 20.
- extract: POST /sdk/content/snippets — the query-relevant page-excerpt
route behind `pplx content snippets` (the CLI's `content fetch` is
deprecated upstream). web_extract has no query, so the URLs' path words
serve as the relevance query; per-URL `error` entries survive a 200.
- Wired into the same touchpoints as the other keyed vendors: legacy
backend set + credential ladder + availability probe (web_tools),
registry preference walk, OPTIONAL_ENV_VARS, `hermes config`/status/
dump key lists, nous_subscription direct-credential detection, setup
summary, test conftests, docs.
Not a keyless-ring member (Perplexity has no anonymous tier). Related
closed PRs #9192 / #23981 / #45225 predate the plugin ABC.
Off should mean the model is never told the tool exists. A switch that
only made the call fail leaves Hermes offering walkthroughs it cannot
give and promising to point at things it cannot point at, which reads as
a broken agent rather than a respected preference.
Both gate on the switch through a shared desktop_ui.user_enabled helper,
which is the reactions check_fn generalized — same config read, same
reason it has to be config rather than an env var: the switch belongs to
the session's client, and the client may be on another machine.
- Tavily plugin deleted (plugins/web/tavily), keyless endpoints and
ring entry removed from keyless_mcp, legacy backend set / credential
ladder / preference walks / rescue key map scrubbed.
- TAVILY_API_KEY deregistered across config, setup, status, dump, and
nous_subscription surfaces. The tvly- redaction pattern stays --
legacy keys in user envs still deserve masking.
- Sibling test pins migrated (keenable/exa stand in where tavily was
the fixture vendor); tavily test suite deleted.
- Docs updated: web-search, configuration, integrations,
environment-variables, tools-reference, web-dashboard, provider
plugin dev guide.
Live-verified from an isolated HERMES_HOME with all web creds blanked:
zero-config resolution lands in the 4-vendor ring, live keyless ring
search succeeds, no tavily anywhere in resolution order.
The todo tool now supports hierarchical task lists: an item's optional
'parent' field points at another item's id, making it a subtask.
- tools/todo_tool.py: parent validated (self-ref dropped), dangling refs
and cycles sanitized; merge mode can set/clear parent; post-compression
injection renders the tree indented and keeps a finished parent visible
while any descendant is still active; the in-progress reorder pass is
skipped for nested lists (a flat move would tear subtasks from parents).
- Schema cost: ~45 tokens added to the cached tool schema (one string
property + one behavior sentence).
- acp_adapter/tools.py: todo result markdown indents by parent depth.
- Desktop: TodoItem carries parent; todoTree() DFS helper; composer
status stack renders subtask rows indented (depth-capped), stabilizer
compares depth.
- Docs: tools-reference todo entry mentions nesting.
Hydration/replay paths (gateway fresh-agent, API-server history) work
unchanged: parent rides inside the same todos array.
Made opt-in when it fired a tip 45 seconds into a launch and another
every six minutes, which is a cadence that owes you a choice. The pacing
has since become a settling delay of five to ten minutes per launch and
a six-hour cooldown persisted across them — roughly a tip a day, weeks
to walk the catalog. At that weight the switch has nothing left to
protect anyone from, and a discovery feature nobody meets is one nobody
has. The switch stays for whoever still wants it off.
A first tip 45 seconds in and one every six minutes after walks the
whole catalog in an hour, which is the cadence of a notification rather
than a nicety. Games get this right by being almost absent: a tip while
you settle in, then nothing for the rest of the day.
Two clocks now have to agree. A per-launch settling delay of five to ten
minutes means opening the app is never met with a bubble, and a six-hour
cooldown persisted across launches means quitting and reopening isn't a
way to farm them — the old schedule lived in the effect and re-armed on
every mount. Flipping the switch on skips the settling delay and offers
immediately, since that clock guards a launch you came into with a
purpose, not a deliberate opt-in.
An agent tip starts the cooldown too: whoever just pointed at something,
the user has had their one interruption for a while.
The two halves of tips were behind one switch, which meant the app
volunteering commentary at idle shipped on by default. Split them along
the line that matters: the rotation talks unprompted, so it now waits to
be asked for, while an agent tip stays ungated like the tour it mirrors
— Hermes raises one mid-conversation, in answer to something the user
said.
Drops the tool's config gate along with the config key it read. The
renderer mirrored that key with config.set, which has no branch for it
and answered "unknown config key" into a swallowed catch, so the opt-out
never reached the backend in the first place.
The quiet sibling of `tour`, in the same `desktop_ui` toolset and reading the
same `tour(action='targets')` discovery call: one bubble with an arrow, for a
sentence that would be clearer with a finger on the thing it's about. Dimming
the whole app to say "the model name is a button" is the wrong weight.
Fire-and-forget rather than a round-trip, because a tip is not a question and
blocking the turn on one would stall the reply it belongs to. The renderer
enforces the user's opt-out itself, so a stale config read can never put a
bubble on a screen that asked for none.
Every drive_preview action answered with the entire inventory — around 120
elements of ref, role, label, and an up-to-eight-rung `:nth-child` selector
chain. On a real app shell that was ~24.5k characters, re-sent after every
click, so a ten-step task paid for ten copies of a page that had barely moved.
Handles are now durable and legible. An element is named after what it is and
what it says — `btn-sign-in`, `inp-email`, `srch-search-projects` — minted once
per page and never reused, with duplicates disambiguated as `btn-edit`,
`btn-edit-1`. Each one remembers a stable attribute, its role, its accessible
name, and the nearest landmark it sits in, so when a framework destroys the
node and builds a new one the handle moves across and the agent is told
`rebound` rather than being handed a removal it has to react to and an addition
it has to re-read. The re-bind ladder is anchortree's (Apache-2.0), minus its
geometry rung, which can never clear the threshold on its own.
Because the handles hold, the first look at a page returns the inventory and
every look after it returns only what moved. `changed` carries the ref and
whichever of label/value/disabled actually shifted — role and selector are
absent by construction, since a change in either would mean the re-bind ladder
was looking at a different element. A delta gives way to a full re-read when
half the page is new, where there is nothing left to reuse.
The selector column is gone with it. It was 74% of the inventory on an
85-element page, nothing downstream ever read it, and a positional chain is
wrong the moment a sibling appears. An `#id` or `[data-testid]` survives when
the page offers one; everything else is addressed by handle.
Legibility is what makes the delta work rather than a nicety. `+ btn-sign-in`
on turn nine reads on its own, where `+ @e42` sends the model back to an
inventory twenty thousand tokens ago.
Measured on an 85-element app shell: 18,693 -> 4,930 characters for a baseline,
and a steady turn that moved two things costs ~200.
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.
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.
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.
The batch card previously locked each answer with its own Continue
press. Now picks and typed answers stage locally, and one Confirm and
continue button (enabled when every question has an answer) submits
the whole batch. Staged answers stay editable until that confirm.
The wire protocol is unchanged. The confirm sends the per-question
locks in sequence, because the last lock resolves the blocked tool and
each earlier lock must already be accepted when it lands. Replayed
locked answers from a reconnect pre-stage their questions so restored
progress stays visible. The TUI and CLI keep incremental per-question
locks, so a timeout there still returns partial answers.
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.
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.
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.
* 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.
The top-level delegate_task description repeated content the model already
receives through parameter descriptions: the concurrency limit (tasks param),
the full nesting clause (role param), context-passing guidance (goal/context
params), and background semantics (background param). Every API call paid for
the duplication (~4,000 chars).
The description now carries only what exists nowhere else in the schema:
use/don't-use routing (execute_code, cronjob), the no-poll rule, the
non-durability warning, the self-report verification contract with concrete
verbs, the language-passing example, the leaf blocked-tool list, and model
inheritance. 3,963 -> 1,704 chars (~570 tokens saved per API call), and the
top-level text is now static (dynamic limits flow only through the two param
descriptions, which are already rebuilt per get_definitions() call).
A/B benchmark across 4 models (gpt-4o, gpt-4o-mini, claude-haiku-4.5,
llama-3.3-70b) showed the naive compaction in PR #72813 regressed weaker
models on exactly the passages it cut (side-effect verification 8/8->0/8 on
gpt-4o-mini; language passing 3/3->0/3 on haiku-4.5). This version keeps
those benchmark-sensitive hooks verbatim.
Tests pin the contracts at keyword level (not prose-literal) plus a size
ceiling, and verify dynamic limits still reach the model via the tasks/role
param descriptions.
Refs #72737, supersedes the delegate_task half of PR #72813.
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.
Cross-checked website/docs against the source at main HEAD and corrected
documented commands, env vars, config keys, headers, and default values
that don't match the code. Docs-only; no behavioral changes.
Refs #36048
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
* 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.
* feat(image-gen): add image-to-image / editing to image_generate
Brings image generation to parity with video generation: the unified
image_generate tool now edits/transforms a source image (image-to-image)
when given image_url / reference_image_urls, routing to each backend's
edit endpoint, exactly as video_generate routes to image-to-video.
- ImageGenProvider ABC: generate() gains keyword-only image_url +
reference_image_urls; new capabilities() declares modalities +
max_reference_images (defaults to text-only, backward compatible).
success_response gains a modality field; adds normalize_reference_images.
- image_generate tool: schema exposes image_url + reference_image_urls;
dynamic schema reflects the active model's actual edit capability so the
agent knows when image_url is honored. Handler + plugin dispatch forward
the new inputs; legacy/text-only providers get a clear modality_unsupported
error instead of silently dropping the source image.
- In-tree FAL: 7 models gain edit endpoints (flux-2-klein, flux-2-pro,
nano-banana-pro, gpt-image-1.5, gpt-image-2, ideogram/v3, qwen-image)
with per-model edit_supports whitelists + reference caps; routes to the
/edit endpoint and skips the upscaler for edits.
- Plugins: openai (images.edit, 16 refs), xai (/v1/images/edits via
grok-imagine-image-quality, JSON body per xAI docs), krea
(image_style_references, 10 refs). openai-codex stays text-only and
rejects edits with an actionable error.
- Tests: 15 new (payload, routing, dispatch forwarding, dynamic schema,
capabilities); updated 2 change-detector/lambda tests for the new schema.
- Docs: image-generation feature page, image-gen provider plugin guide,
tools reference.
* fix(image-gen): preserve legacy passthrough in fal/krea plugin tests
Two existing plugin tests asserted pre-image-to-image behavior:
- fal: forward image_url/reference_image_urls only when supplied, so a
text-to-image delegation stays byte-identical (no None kwargs).
- krea: keep dict-shaped image_style_references refs verbatim (the unified
string refs go through normalize_reference_images; legacy non-string ref
objects pass through unchanged) — fixes KeyError when callers pass the
richer Krea ref-object shape.
* fix(image-gen): clearer not-capable message for text-to-image-only models
When a text-to-image-only model (incl. gpt-image-2 on the Codex OAuth path,
which can't do editing through the Responses image_generation tool) gets a
source image, say 'this model is not capable of image-to-image / editing —
provide a text-only prompt' rather than sending the user shopping for other
backends. Applies to the openai-codex guard, the in-tree FAL no-edit-endpoint
error, and the dynamic tool-schema text-only line.
The locale switcher appeared broken because hardcoded markdown links
(`](/docs/X)`) got double-prefixed by Docusaurus to `/docs/<locale>/docs/X`
(404) in non-English locales, and the MDX hero `<a href>` on the index
page escaped locale routing entirely.
Changes:
- Rewrite 922 `](/docs/X)` -> `](/X)` across 166 docs files (strip trailing
.md too). Docusaurus prepends locale + baseUrl itself.
- docs/index.md -> index.mdx; hero "Get Started" anchor -> Docusaurus
<Link> so it stays inside the active locale.
- Drop `ko` locale entirely from docusaurus.config.ts + delete i18n/ko/
(4 stale auto-translated kanban pages, <2% coverage, misleading).
Verified `npm run build` succeeds for both en and zh-Hans; `build/zh-Hans/
index.html` has no /docs/zh-Hans/docs/... double-prefixed paths.
PR2 will translate the 335 English docs into i18n/zh-Hans/.
X Premium+ also grants Grok OAuth access — the 'SuperGrok Subscription'
wording suggested SuperGrok was the only entitlement path. Updated to
'SuperGrok / Premium+' across the picker label, setup wizard, auth flows,
and docs so Premium+ subscribers know the row applies to them too.
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.
* feat(session_search): single-shape tool with discovery, scroll, browse — no LLM
Replaces the LLM-summarized session_search with a single-shape tool that
returns actual messages from the DB. Three calling shapes inferred from
args (no mode parameter):
1. Discovery — pass query. FTS5 + anchored ±5 window + bookends per hit,
all in one call. ~20ms on a real DB instead of ~90s for the previous
three aux-LLM calls.
2. Scroll — pass session_id + around_message_id. Returns a window
centered on the anchor. To paginate, re-anchor on the first/last id
of the returned window. Boundary message appears in both windows
as the orientation marker. ~1ms per scroll call.
3. Browse — no args. Recent sessions chronologically.
Bookend_start (first 3 user+assistant msgs) and bookend_end (last 3) give
the agent goal + resolution on every discovery hit, so a single tool call
reconstructs a long session's arc without loading the whole transcript.
The aux-LLM summary path is gone: it cost ~$0.30/call, took ~30s, and
laundered FTS5 hits through a model that could confabulate when the right
session wasn't in the hit list. The merged shape returns byte-for-byte
content from SQLite.
History:
- PR #20238 (JabberELF) seeded the fast/summary dual-mode split.
- PR #26419 (yoniebans) expanded to fast/guided/summary with bookends,
multi-anchor drill-down, default-mode config, and a teaching skill.
This PR collapses that toolkit into one shape with explicit scroll
support, drops the summary path, drops the mode parameter, drops the
config knob, drops the skill. JabberELF's seed work is acknowledged via
the AUTHOR_MAP entry.
Validation:
- 38/38 tool tests pass (tests/tools/test_session_search.py)
- 12/12 get_messages_around tests pass (tests/hermes_state/)
- 11/11 get_anchored_view tests pass (tests/hermes_state/)
- Full tests/tools/ run: 5168 passing, 2 failures pre-exist on main
(test ordering in test_delegate.py, unrelated)
- E2E against live state DB: discovery 20ms, scroll 1ms, browse 280ms;
pagination forward+backward works with boundary-message orientation;
error paths return clean tool_error responses
Co-authored-by: JabberELF <abcdjmm970703@gmail.com>
Co-authored-by: yoniebans <jonny@nousresearch.com>
* chore(session_search): prune dead LLM-summary config and docs
Companion to the single-shape rewrite. The auxiliary.session_search config
block, max_concurrency / extra_body tunables, and matching docs sections
all referenced the removed LLM summarization path. Removing them so users
don't try to tune knobs that nothing reads.
- hermes_cli/config.py: drop dead auxiliary.session_search block from
DEFAULT_CONFIG. Leftover keys in user config.yaml are harmless and
ignored.
- hermes_cli/tips.py: drop two tips referencing the removed
max_concurrency / extra_body knobs.
- website/docs/user-guide/configuration.md: drop 'Session Search Tuning'
section and the auxiliary.session_search block from the example.
- website/docs/user-guide/features/fallback-providers.md: drop session_search
rows from the auxiliary-tasks tables and the dedicated tuning subsection.
- website/docs/reference/tools-reference.md: rewrite the session_search
entry to describe the new three-shape behaviour.
- CONTRIBUTING.md: update the file-tree description.
- tests/tools/test_llm_content_none_guard.py: remove TestSessionSearchContentNone
class and test_session_search_tool_guarded — both guard against an
unguarded .content.strip() call site in _summarize_session() that no
longer exists.
Validation: 97/97 targeted tests still pass (hermes_state + session_search +
llm_content_none_guard). Config tests 55/55.
---------
Co-authored-by: JabberELF <abcdjmm970703@gmail.com>
Co-authored-by: yoniebans <jonny@nousresearch.com>
The video_gen toolset and its video_generate tool shipped without
user-facing reference docs. toolsets-reference.md and the dev-guide
plugin page were already in, but reference/tools-reference.md had no
video_gen section at all and user-guide/features/tools.md's Media row
didn't list video_generate.
- reference/tools-reference.md: add a video_gen section after video,
including backend list (xAI Grok-Imagine, FAL.ai Veo/Pixverse/Kling),
unified text-to-video / image-to-video surface note, link to the
dev-guide plugin page, and the video_generate tool row. Add
video_generate to the standalone-tools quick-counts line.
- user-guide/features/tools.md: extend Media row with video_generate
and video_analyze plus an opt-in caveat.
* 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>
* 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.
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.
