Files
hermes-agent/ui-tui
Siddharth Balyan 70f5dc5f46 feat(connectors): the backend API for the desktop Connectors page; connect an app without a chat session (#115191)
* feat(connectors): the backend serves a connector's tool list, cached for 24 hours

The Connectors page opens one app and shows every tool it has. The backend
had no way to read that list.

- `tools/connectors/portal/`: a client for the portal's tool-list route and a
  JSON cache under the Hermes home, one file per portal origin and connector.
  An entry is fresh for 24 hours. After that the read revalidates with the
  stored ETag: 304 keeps the list, 404 deletes the entry, an upstream failure
  serves the stored list marked stale, and a 401 never serves the cache.
- `connectors.tools {slug, refresh}`: account-level, routed by `profile`, no
  chat session. Errors carry a fixed `reason` from one closed set on the rail.
- Every connector model that is not operation state moves into
  `tui_gateway/contracts/connectors.py`. Handlers that no chat session owns
  live in `tui_gateway/methods_connectors_account.py`.

The wire model is tolerant: an unknown facet reads as unclassified and one odd
tool never blanks a connector.

* feat(connectors): catalog, accounts and member tool rules by RPC

The Connectors page needs the app catalog, the connected account of one app,
a way to disconnect it, and the member's own on/off rules. None had an RPC.

- `connectors.catalog`: name, description, category and logo of each app.
- `connectors.accounts`, `connectors.accounts.remove`: read the accounts at
  the tool gateway and remove one by id.
- `connectors.policy.get`: the rule layers that apply to the member, widest
  first. The body is a union on `mode`, so a reader can name who turned a
  tool off.
- `connectors.policy.set`: one change, a union on `type` (the tools of one
  connector, or one connector on or off), with the revision the user saw. A
  stale revision answers `POLICY_CONFLICT`. The backend composes the upstream
  write in one pure function, so no renderer learns the upstream rules.
- Bundled MCP manifests can name their hosted twin with `connector:`, so the
  page can show one card per app.

* feat(connectors): connect an app without a chat session

Every connector RPC took a `session_id`, and a connect that did not come from
the model's tool call minted a link with no watcher. The Connectors page has
no chat session, and its card must flip to connected by itself.

- `connectors.list`, `connectors.connect`, `connectors.operation.status`,
  `connectors.operation.wake` and `connection.respond` take `owner`, a union
  on `type`: `session` (today's behaviour and authorization) or `account`
  (routed by `profile`, authorized by the live transport like `mcp.*`).
  `session_id` is gone from these params; every desktop caller sends `owner`.
- An account connect runs the same operation lifecycle on a background
  thread, under the profile's scope, so the watcher reads the account and
  settles the operation. A second connect for an app that is already
  connecting returns the open operation and mints nothing.
- `connection.update` carries `owner`. An account operation has no session to
  address, so its updates go out on the session-less broadcast path.

* feat(mcp-catalog): eighteen more bundled entries name their hosted connector

A bundled MCP entry and a hosted connector for the same app are one card
on the Connectors page only when the manifest names its hosted twin.
Linear and Notion had the field. These entries get it too: airtable,
asana, attio, calendly, dropbox, figma, railway, supabase, todoist,
betterstack, canva, cloudflare, datadog, intercom, neon, sentry, stripe
and vercel. Atlassian maps to two hosted connectors and Prisma Postgres
is not clearly the same app, so both stay without one.

* refactor(connectors): the account handlers share one gate, one params model and one write table

The six account-level handlers each repeated the availability gate, the
auth catch and the catch-all reply. One decorator now owns that, and each
handler validates its params with its contract model instead of a ladder
of isinstance checks. The five connection RPCs share one guard for the
unexpected-failure reply.

The four write composers for the member rules were the same function
with a different list key and polarity. They are one table now.

The owner union lives in contracts/common.py, so the params side and the
event side stop declaring it twice and the import cycle is gone.

An account operation start carries one event and a flag, so the wait for
the sign-in link blocks instead of polling every 50 ms. run_operation
loses its two account-only parameters; drive_operation is the second
entry point.

Tests: four deleted (they exercised pydantic or the mock), three merged
into tables, two added (a client that still sends the old top-level
session_id is refused; all six account RPCs run off the server loop).
The shared reply helper and the HTTP and managed-client fakes move to
one place each. Comments are one line or gone.

* fix(connectors): a missing tool-list route reads as "unavailable", not "connector gone"

The tool-list read treated every 404 as the portal's "this connector is
not in the catalog" answer. It deleted the cache entry and answered
CONNECTOR_NOT_FOUND, so a page would offer to remove an app that is
connected and works. A portal that does not serve the route yet answers
a bare 404 for every app.

Only the portal's own {"error": "connector_not_found"} means the
connector is gone. Any other 404 is now a tool-list outage: the cached
list is served as stale, or the RPC answers TOOLS_UNAVAILABLE.

* fix(connectors): a connect from the page returns to the app after sign-in

The sign-in link carries a return target only when the session's surface
is the desktop. A chat session binds that surface. An account-owned call
has no chat session, so nothing bound it: the link was minted without a
return target and the browser ended on the portal's done page instead of
coming back to Hermes.

Every account-owned call now runs with the process's own surface bound,
next to its profile scope. The operation thread copies that context, so
the first link and every reissued link carry the return target and the
operation id.

* test(connectors): defer the new connector RPC coverage

The tests for the new account RPCs, the portal client, the tool-list cache
and the rule composer leave this PR and come back in one later change, after
the API is settled. The same was done for #111008.

Kept: the edits that existing tests need because the five connection RPCs
now take `owner` instead of `session_id`, and the rename of the managed
client seam.

Removed: six new test files, their two fakes and the gateway conftest, and
the new cases in test_mcp_catalog.py, test_connectors_gateway_client.py,
gateway-rpc.test.ts and notifications.test.ts. Reverting this commit restores
all of them.

* fix(cli): the connection panel hands the tool thread back at once

The classic CLI's connection callback waited on a queue for the user's first
decision. The operation's watcher starts only after the callback returns, and
the watcher is what polls a hosted account, runs the 300-second deadline and
sees Ctrl+C.

For a hosted connector the panel opens on the sign-in link, where the only
key that filled the queue was Cancel. The account was never polled: the user
signed in, the panel never changed, and Esc reported the app as skipped.
Ctrl+C set the interrupt flag but left the thread parked on the queue, so the
turn never ended.

The callback now opens the panel and returns, as the gateway's callback does
for the desktop and the Ink TUI. The panel's actions already reach the
operation through apply_answer on the UI thread, so the queue is removed. An
install with a form still waits for Connect, because the backend starts no
work for a pending row. Ctrl+C now settles the operation as `interrupt`, and
open rows become `not_connected`.

Checked on the e2e rig with the fake tool gateway: hosted connect completes on
the third status read; Ctrl+C ends the turn and the polling stops; an MCP
install with a plain and a secret field still saves config and both values.

* fix(connectors): "run it again" lives in the library, so the classic CLI can use it

Making a new sign-in link for a failed or expired hosted connector was
implemented only in the JSON-RPC layer (`_reissue`). The classic CLI does not
go through JSON-RPC: its Connect button on a failed row called apply_answer,
which does nothing for a hosted operation because it has no MCP runner. The
panel showed "Waiting…" until the deadline.

`tools.connectors.run.reissue(operation, names)` now holds the checks and the
per-kind action, and returns a refusal reason or None. The gateway maps each
reason to the same JSON-RPC error as before. The CLI calls it for a hosted
row; a refusal is shown on the row. MCP rows keep their path, because Connect
on a failed MCP row re-sends the form values.

Checked on the e2e rig: a scripted failed sign-in, then Connect: a second mint
with `reinitiate: true`, a new link with a new connection id, then connected.

* feat(connectors): the account list and disconnect go through the portal

`connectors.accounts` and `connectors.accounts.remove` called the tool
gateway. They now call the portal's account-management routes
(`GET /api/v1/connectors/accounts`, `DELETE /api/v1/connectors/accounts/{id}`),
which apply the organisation membership checks and write the disconnect audit
row. There is no fallback to the gateway when the portal is unavailable, and a
removal is never retried.

The read of ONE account stays on the gateway (`GET v1/connectors/accounts/{id}`):
the portal has no such route, and the operation watcher polls it once per second.

`ConnectorClient.list_accounts` and `delete_account` are removed. The removed
account's reply model carries `connector`, which both services send.

* fix(connectors): the account RPCs answer what the portal really sends

Checked against the portal source and against the staging and production
services.

- Errors are read from the upstream error code, not the HTTP status. A rule
  write answered 409 for a stale revision and for a user with no organisation;
  both read as "the policy changed". `org_required` is now `ORG_REQUIRED` and
  403 `no_access` is `ORG_ACCESS_DENIED` on every account RPC; only a rejected
  sign-in is `NEEDS_NOUS_AUTH`. `connectors.list` and `connectors.connect` with
  the account owner map these too.
- `connectors.policy.get` and `connectors.policy.set` carry `effective`: the
  portal's own result for this user, with its stamp and without provider or
  subject ids. Nothing is recomputed locally.
- A rule write needs the revision the user saw: `expected_revision` is required
  and must be a revision string; a bad one is refused before any HTTP call.
- A tool row carries `no_auth`; a list without the upstream flag is an invalid
  answer, not `false`.
- `connectors.accounts.remove` returns the app of the removed account. An
  invalid id is `INVALID_PARAMS`.
- The tool-list cache is per signed-in member (a hash of the token's `sub`),
  so two Nous accounts on one profile do not share entries.
- A malformed slug is a local error, not a 404 from a server nobody called.

Live, staging: no revision and a malformed revision refused locally; a good
revision wrote one disabled Gmail tool and returned it in `effective`; the
same revision again answered `POLICY_CONFLICT`; the list row showed the tool;
the restore brought the member rules back to the start. Live, staging and
production, read-only: all 60 tool lists (5483 tools) parse.

* fix(connectors): the operation RPCs match their contract; a settled card cannot start a new link

Found by two adversarial reviews of the RPC layer and its types.

- `connectors.connect` from a chat session with no open operation is refused
  (`UNKNOWN_OPERATION`). It used to call `manage_connections` through the tool
  registry with no card: it made a link nobody watched, returned a reply
  without the required `settled` field, and named an operation that was never
  registered. There is one way into an operation: the agent's call, or the
  account owner's `connectors.connect`. "Run it again" inside an open
  operation is unchanged.
- `connection.update` for a session is routed by session key AND profile; two
  profiles with the same key no longer cross-deliver a sign-in link. The event
  payload gets the same redaction as the RPC replies.
- `connection.respond` runs on the long-handler pool: an approval can start MCP
  OAuth discovery, which blocked every RPC of the gateway while it ran.
- `connectors.list` rows are a closed snake_case model: `connector`, `enabled`,
  `connected`, `connection_status`, `status_reason`, `gateway_disabled_tools`.
  The last one is display data: the gateway enforces the rules, the backend
  only passes the list on. The phantom `name` and `description` are gone, and
  the desktop uses the generated types instead of hand-written copies.
- `tools_listing` (model-only data) no longer rides on `connectors.operation.status`.
- `unavailable` is removed from the target states and settle reasons: nothing
  produces it. The contract generator now fails when a contract enum and its
  domain enum differ.
- `ConnectorErrorReason` is part of the generated TypeScript and OpenRPC.
- The desktop sends `connection.respond` on the socket that holds the session,
  as wake and reissue already did.
- Contract violations are logged every time, at error level.
- An account connect whose prepare step is slow returns the live operation
  instead of an error while the operation keeps running.
- The MCP-manifest `connector` field leaves this PR (it moves to a later one
  on top of the catalog-reader change). `hermes_cli/mcp_catalog.py` and
  `optional-mcps/` are untouched by this PR again.

anti-slop: no net-new findings (15 touched files).

* fix(connectors): the model gets no sign-in link wherever a card exists; side agents cannot connect

The flag that tells the model "a connection card exists" was the session
platform (`== "desktop"`). The Ink TUI and the classic CLI also draw a card,
so there a connector call on an unconnected app handed the model the raw
`connect_url` and told it to pass the link to the user.

- The agent turn now declares how a link can reach the user
  (`tools/connectors/turn.py`): CARD when the agent was built with a
  connection callback, SIDE for a subagent or a background turn, LINK for a
  headless run (`-q`, cron, ACP, api_server, messaging). It is set once per
  tool batch in the agent loop and read by the connector dispatch path, which
  never sees the agent. The session platform decides return-to-app only.
- CARD: the result carries `connect_card_available` and our hint, never the
  link and never the gateway's own hint.
- SIDE: subagents (`delegate_tool`), gateway background turns and the classic
  CLI `/bg` are built with `side_agent=True`. They hold no `manage_connections`
  tool on any path that derives the tool list, and a connector call on an
  unconnected app gets no link, only "report this to the main agent".
- LINK is unchanged.
- The hosted path with no card builds a detached operation, as the MCP path
  does, so no `connection.update` is emitted for an operation no client asked
  for. Names and docstrings that said "off desktop" now say "no card".
- A settled card is dead on the desktop: `reissueConnectionTarget` and
  `respondToConnectionRequest` share one guard and send nothing for a settled
  or unknown operation.
- The model-facing settled result no longer carries `connection_id`; the model
  repeated it to the user.

Shown on the real clients with a real model (rig, fake tool gateway): Ink TUI
and classic CLI get `connect_card_available` and no link, the model opens the
card, the account connects, the retried call succeeds; `-q` still gets the
link; a subagent and a background turn have no `manage_connections` and get
the no-link hint; on the desktop a card settled with Continue has no enabled
control and sends no RPC.

* feat(tools): every call made through tool_search + tool_call shows a real label on all three clients

A bridged call showed as a generic `tool_call` row in the Ink TUI and as
`⚡ tool_call` in the classic CLI, because the display looked the name up in
the tool registry and bridged names are made at run time. The desktop labelled
only batches that were all hosted connector calls, by parsing names itself.

- `tools/tool_labels.py` is the one place that turns a bridged call into a
  label: kind, app, action, emoji and text. Hosted: `connectors__gmail__GMAIL_SEND_EMAIL`
  → "Gmail · send email". MCP: "Linear · list issues". A local deferred tool
  keeps its own emoji, verb and primary-argument preview. A batch gets exactly
  one label per entry, always; an entry with no name gets a generic label.
- Classic CLI: one row per inner call; the duration on the last row; the
  failure text on the row of the call that failed. With friendly labels off
  it prints what it printed before.
- Gateway: tool start, progress and complete events and stored transcript rows
  carry a typed `labels` field. It does not depend on the classic CLI's
  display setting. Clients no longer parse tool names.
- Ink TUI: rows from the labels; the verbose trail keeps Args and Result.
- Desktop: `ConnectorExecution` renders hosted, MCP and mixed turns from the
  labels, one row per call. The labels reach the row under a key no tool
  argument can use. The connect card it drew under a failed tool result is
  gone: after `CONNECTION_REQUIRED` the one way in is the agent's own
  `manage_connections` call.
- `tool_search` and `tool_describe` rows read "Searching tools · <query>" and
  "Reading tool details · N tools".

Shown on the real desktop (video and screenshots), the Ink TUI and the classic
CLI with the rig: hosted rows, MCP rows, a two-entry batch, a failed entry, a
`CONNECTION_REQUIRED` row with no card under it, labels after a reload, and the
desktop rows with the classic CLI setting off.

* fix(connectors): the model can tell "hosted tools unavailable" from "no such tool"; manage_connections routes MCP names correctly

- A failed hosted search or describe used to return nothing, by design, so the
  model saw only local tools and told the user that a connected app was
  missing. The local results are unchanged; when the hosted leg failed, the
  `tool_search` and `tool_describe` results carry
  `connectors: {status: "unavailable", reason: "unreachable" | "sign_in_expired"}`
  and one hint line. A rejected token is `sign_in_expired`; an entitlement
  refusal or a shut gate adds nothing. `tool_describe` no longer lists those
  names under `not_found` next to "search again".
- NS-932. The description now says which side a name belongs to: a bare name
  is a hosted connector account; `mcp: true` only when the user asks for an MCP
  server, a local server or an install, or when the name exists only in the
  catalog; connect and reconnect are hosted verbs, install, enable and
  authorize are MCP verbs. It names the three clients that draw a card.
- A misrouted target is refused with the call that works. Only when the
  gateway does not know the connector (confirmed on that failure path) and the
  name is a catalog entry does the target fail with "X is a local MCP server.
  Call manage_connections with action install ...". It is a per-target
  outcome: other targets of the same call keep their links and their card. A
  vendor failure on a name both sides know stays an ordinary failed row. The
  MCP side mirrors it, and never for an entry that is only not installed.
- "Do not re-ask after a skip or a timeout" no longer stops the model when the
  USER asks for that app again; the description and the settled-result notes
  say so. A builder saw the model refuse a direct user request.

Shown on the Ink TUI and the classic CLI with a real model: a dead gateway and
a 401; "connect fxmail" goes hosted; "install the fx-noauth MCP server" goes
MCP; "connect fx-noauth" reaches the MCP install card in one corrective round
with no hosted mint; a two-target call where one is misrouted still connects
the other with exactly one mint.

* fix(tui): the connection card answers every key, shows what is happening, and is dead once settled

Reproduced on the real Ink TUI with the rig, then fixed:

- The keyboard was dead during the sign-in wait: the card kept a `submitting`
  flag that the normal OAuth path never cleared, and Esc went through the same
  guard. The in-flight state now belongs to the answered row and clears when
  that row moves, when any later frame of the operation arrives, or after
  five seconds. Esc skips the row in every phase; Ctrl+C interrupts the turn
  (the input handler had no branch for this overlay); Shift+arrows scroll the
  transcript and the card ignores them; arrow keys no longer move the text
  cursor and the field focus at once.
- The card was lost at turn idle: the overlay flag was cleared while the
  operation stayed in the store, and a resume dropped the pending card. The
  flag survives idle, a resume shows the pending card again, a session switch
  clears it.
- States with no branch: `not_connected` and a row with no link fell into the
  credential form; `expired` vanished with no note. The title and the row text
  now name the action (connect, reconnect, install, enable, authorize); a
  failed or expired row with no fields offers Try again / Skip; a failed row
  WITH fields reopens the form over the typed draft, with the failure above it.
- A settled card is dead: at settle the overlay closes and one transcript line
  per app states the outcome. A settled or dismissed operation id is
  remembered, so no replay or resume can reopen its card. Esc in the last
  "Finishing…" moment hides the card and still writes the outcome lines.
- A failed `connection.respond` and a browser that did not open are shown on
  the card in one sentence.

Also: `tui_gateway/connector_payload.py` redacted the BOOLEAN `secret` flag of
a credential field to the string "[REDACTED]". On the desktop every credential
field therefore rendered as a password and lost its prefilled default. A
boolean is no longer redacted.

* chore(connectors): remove the comments and docstrings this branch added

Deletions only. Kept: tool directives (`# noqa`, `// eslint-disable`, ...),
`// SAFETY:` lines, and the docstrings of the contract models under
`tui_gateway/contracts/`, which become the descriptions in the generated
OpenRPC and TypeScript.

Checked that no code changed: every Python file has the same AST as before
once docstrings and `pass` are ignored (62 files), and every TypeScript file
prints the same with comments stripped by the TypeScript printer (32 files).
The generated contract files are unchanged.

* fix(connectors): a card restored after a reload answers again; every account RPC names auth and org failures

Found by the end-to-end runs on the pushed head.

- Desktop: after a window reload, Continue on the restored card sent nothing.
  The answer looked up the backend that holds the session with the runtime
  session id, the lookup wants the stored id, and a failed lookup returned
  silently. When the lookup gives no owner the answer now goes out on the
  window's active socket, which is what main does.
- `connectors.policy.get` answered `POLICY_UNAVAILABLE` for a rejected sign-in,
  a refused scope, a non-member and a missing organisation alike: the handler
  runs with the gateway's globals and did not import the reason enum, so its
  own error mapping raised. `connectors.accounts.remove` caught auth failures
  in its generic branch. `org_required` was mapped on `policy.set` only. All
  six account RPCs now answer `NEEDS_NOUS_AUTH`, `FORBIDDEN_SCOPE`,
  `ORG_ACCESS_DENIED` and `ORG_REQUIRED` for those four upstream answers.
2026-09-22 13:57:51 +05:30
..

Hermes TUI

React + Ink terminal UI for Hermes. TypeScript owns the screen. Python owns sessions, tools, model calls, and most command logic.

hermes --tui

What runs

The client entrypoint is src/entry.tsx. It exits early if stdin is not a TTY, starts GatewayClient, then renders App.

GatewayClient spawns:

python -m tui_gateway.entry

Interpreter resolution order is: HERMES_PYTHON → PYTHON → $VIRTUAL_ENV/bin/python → ./.venv/bin/python → ./venv/bin/python → python3 (or python on Windows).

The transport is newline-delimited JSON-RPC over stdio:

ui-tui/src                  tui_gateway/
-----------                 -------------
entry.tsx                   entry.py
  -> GatewayClient            -> request loop
  -> App                      -> server.py RPC handlers

stdin/stdout: JSON-RPC requests, responses, events
stderr: captured into an in-memory log ring

Malformed stdout lines are treated as protocol noise and surfaced as gateway.protocol_error. Stderr lines become gateway.stderr. Neither writes directly into the terminal.

Running it

From the repo root, the normal path is:

hermes --tui

The CLI expects ui-tui/dist/entry.js to exist, or the whole source code available in which to run npm install and npm run dev.

cd ui-tui
npm install

Local package commands:

npm run dev
npm start
npm run build
npm run lint
npm run fmt
npm run fix

Tests use vitest:

npm test         # single run
npm run test:watch

Live agents

The dock above the composer appears automatically while children are running. It shows actual live-child counts, task names, elapsed time, and the latest activity. Its row budget shrinks on short terminals; finished work remains in the existing /agents / /replay history rather than permanently occupying composer space. Async completion units are not counted as extra agents.

  • Ctrl+T expands the roster without clearing your draft; Esc returns.
  • ↑/↓ selects an agent, Enter opens its details (tools, output, files, usage).
  • t opens its bounded live transcript tail; g/G moves to top/bottom.
  • e opens a separate steering form. Enter queues guidance and Esc returns. “Queued” means accepted for the next tool boundary, not confirmed delivery.
  • x requests that the selected child stop; X requests a subtree stop.
  • Existing sort/filter, spawn-pause, timeline, and replay controls remain available.

The roster hydrates from the session-scoped subagent.list RPC alongside streamed events. Only an open tail view polls subagent.tail; steering uses the existing subagent.steer RPC. No model tool schema or prompt-caching behavior changes.

App model

src/app.tsx is the center of the UI. Heavy logic is split into src/app/:

  • src/app/createGatewayEventHandler.ts — maps gateway events to state updates
  • src/app/createSlashHandler.ts — local slash command dispatch
  • src/app/useComposerState.ts — draft, multiline buffer, queue editing
  • src/app/useInputHandlers.ts — keypress routing
  • src/app/useMainApp.ts — top-level composition hook: wires all sub-hooks, manages transcript history, session polling, and exposes props consumed by app.tsx
  • src/app/useSessionLifecycle.ts — session create / resume / activate / close and visible-history reset
  • src/app/useSubmission.ts — message send, shell exec (!cmd), inline interpolation ({!cmd}), and busy-input-mode dispatch (queue / steer / interrupt)
  • src/app/turnController.ts — stateful class that drives the turn lifecycle: buffers streaming deltas, manages tool/reasoning state, handles interrupt and message-complete transitions
  • src/app/turnStore.ts — nanostore for turn state (streaming text, tools, reasoning, subagents, todos, activity trail)
  • src/app/useConfigSync.ts — fetches config.get full on session start and polls config mtime every 5 s; applies display settings and triggers MCP reload on change
  • src/app/useLongRunToolCharms.ts — fires ambient activity messages for tools running longer than 8 s
  • src/app/overlayStore.ts / src/app/uiStore.ts — nanostores for overlay and UI state
  • src/app/delegationStore.ts — nanostore for subagent spawning caps and overlay accordion state
  • src/app/spawnHistoryStore.ts — in-memory ring (last 10) of finished subagent fan-out snapshots; populated at turn end for /replay
  • src/app/inputSelectionStore.ts — nanostore exposing the active text-input selection handle
  • src/app/gatewayContext.tsx — React context for the gateway client
  • src/app/gatewayRecovery.ts — pure function that decides whether to respawn and resume after a gateway crash, with a 3-attempt / 60 s budget
  • src/app/setupHandoff.ts — launches external hermes setup, suspends Ink while it runs, opens a new session on success
  • src/app/scroll.ts — scrolls the viewport while keeping the text selection anchor in sync
  • src/app/interfaces.ts — internal interfaces (ComposerActions, GatewayRpc, etc.)

Slash command subsystem (src/app/slash/)

  • types.ts — SlashCommand interface and SlashRunCtx execution context (gateway rpc, transcript helpers, session refs, stale-guard)
  • registry.ts — assembles SLASH_COMMANDS from all command files in registration order (core → billing → credits → session → ops → setup → debug) and exposes findSlashCommand(name) for case-insensitive lookup
  • commands/core.ts — general TUI commands
  • commands/billing.ts — /billing: manage Nous remote spending — buy credits, auto-reload, limits
  • commands/credits.ts — /credits
  • commands/session.ts — session and agent commands
  • commands/ops.ts — operations commands
  • commands/setup.ts — /setup
  • commands/debug.ts — /heapdump, /mem

The top-level app.tsx composes these into the Ink tree with Static transcript output, a live streaming assistant row, prompt overlays, queue preview, status rule, input line, and completion list.

State managed at the top level includes:

  • transcript and streaming state
  • queued messages and input history
  • session lifecycle
  • tool progress and reasoning text
  • prompt flows for approval, clarify, sudo, and secret input
  • slash command routing
  • tab completion and path completion
  • theme state from gateway skin data

The UI renders as a normal Ink tree with Static transcript output, a live streaming assistant row, prompt overlays, queue preview, status rule, input line, and completion list.

The intro panel is driven by session.info and rendered through branding.tsx.

Hotkeys and interactions

Current input behavior is split across app.tsx, components/textInput.tsx, and the prompt/picker components.

Main chat input

Key Behavior
Enter Submit the current draft
empty Enter twice If queued messages exist and the agent is busy, interrupt the current run. If queued messages exist and the agent is idle, send the next queued message
Shift+Enter / Alt+Enter Insert a newline in the current draft
\ + Enter Append the line to the multiline buffer (fallback for terminals without modifier support)
Ctrl+C Interrupt active run, or clear the current draft, or exit if nothing is pending
Ctrl+D Exit
Cmd/Ctrl+G / Alt+G Open $EDITOR with the current draft (use Alt+G in VSCode/Cursor — they bind the primary keystroke to Find Next)
Ctrl+L New session (same as /clear)
Ctrl+V / Alt+V Paste text first, then fall back to image/path attachment when applicable
Tab Apply the active completion
Up/Down Cycle completions if the completion list is open; otherwise edit queued messages first, then walk input history
Left/Right Move the cursor
modified Left/Right Move by word when the terminal sends Ctrl or Meta with the arrow key
Home / Ctrl+A Start of line
End / Ctrl+E End of line
Backspace Delete the character to the left of the cursor
Delete Delete the character to the right of the cursor
modified Backspace Delete the previous word
modified Delete Delete the next word
Ctrl+W Delete the previous word
Ctrl+U Delete from the cursor back to the start of the line
Ctrl+K Delete from the cursor to the end of the line
Meta+B / Meta+F Move by word
!cmd Run a shell command through the gateway
{!cmd} Inline shell interpolation before send; queued drafts keep the raw text until they are sent

Notes:

  • Tab only applies completions when completions are present and you are not in multiline mode.
  • Queue/history navigation only applies when you are not in multiline mode.
  • PgUp / PgDn are left to the terminal emulator; the TUI does not handle them.

Prompt and picker modes

Context Keys Behavior
approval prompt Up/Down, Enter Move and confirm the selected approval choice
approval prompt o, s, a, d Quick-pick once, session, always, deny
approval prompt Esc, Ctrl+C Deny
clarify prompt with choices Up/Down, Enter Move and confirm the selected choice
clarify prompt with choices single-digit number Quick-pick the matching numbered choice
clarify prompt with choices Enter on "Other" Switch into free-text entry
clarify free-text mode Enter Submit typed answer
sudo / secret prompt Enter Submit typed value
sudo / secret prompt Ctrl+C Cancel by sending an empty response
resume picker Up/Down, Enter Move and resume the selected session
resume picker 1-9 Quick-pick one of the first nine visible sessions
resume picker Esc, Ctrl+C Close the picker

Notes:

  • Clarify free-text mode and masked prompts use ink-text-input, so text editing there follows the library's default bindings rather than components/textInput.tsx.
  • When a blocking prompt is open, the main chat input hotkeys are suspended.
  • Clarify mode has no dedicated cancel shortcut in the current client. Sudo and secret prompts only expose Ctrl+C cancellation from the app-level blocked handler.

Interaction rules

  • Plain text entered while the agent is busy is queued instead of sent immediately.
  • Slash commands and !cmd do not queue; they execute immediately even while a run is active.
  • Queue auto-drains after each assistant response, unless a queued item is currently being edited.
  • Up/Down prioritizes queued-message editing over history. History only activates when there is no queue to edit.
  • Queued drafts keep their original !cmd and {!cmd} text while you edit them. Shell commands and interpolation run when the queued item is actually sent.
  • If you load a queued item into the input and resubmit plain text, that queue item is replaced, removed from the queue preview, and promoted to send next. If the agent is still busy, the edited item is moved to the front of the queue and sent after the current run completes.
  • Completion requests are debounced by 60 ms. Input starting with / uses complete.slash. A trailing token that starts with ./, ../, ~/, /, or @ uses complete.path.
  • Text pastes are inserted inline directly into the draft. Nothing is newline-flattened.
  • Cmd/Ctrl+G (or Alt+G in VSCode/Cursor, which intercept the primary keystroke for Find Next) writes the current draft, including any multiline buffer, to a temp file, suspends Ink, launches $EDITOR, then restores the TUI and submits the saved text if the editor exits cleanly.
  • Input history is stored in ~/.hermes/.hermes_history or under HERMES_HOME.

Rendering

Assistant output is rendered in one of two ways:

  • if the payload already contains ANSI, messageLine.tsx prints it directly
  • otherwise components/markdown.tsx renders a small Markdown subset into Ink components

The Markdown renderer handles headings, lists, block quotes, tables, fenced code blocks, diff coloring, inline code, emphasis, links, and plain URLs.

Tool/status activity is shown in a live activity lane. Transcript rows stay focused on user/assistant turns.

Prompt flows

The Python gateway can pause the main loop and ask the client a question. These are JSON-RPC requests from the server (string id, answered with a response frame of the same id — see createServerRequestHandler.ts), not events:

  • approval: allow once, allow for session, allow always, or deny → { choice }
  • clarify: pick from choices or type a custom answer → { answer } (batch: { answers })
  • sudo: masked password entry → { value }
  • secret: masked value entry for a named env var → { value }
  • session.list: used by SessionPicker for /resume

A withdrawn question (timeout, interrupt) arrives as a request.cancel event carrying its id.

These are stateful UI branches in app.tsx, not separate screens.

Commands

The following commands are handled directly by the TUI client. Unrecognized commands fall through to the Python gateway via slash.exec and command.dispatch.

Core (core.ts)

/help, /quit (alias /exit), /update, /clear (alias /new), /density, /copy, /paste, /details (alias /detail), /statusbar (alias /sb), /queue (alias /q), /logs, /history, /save, /undo, /retry, /steer, /mouse (alias /scroll), /status, /title, /fortune, /redraw, /terminal-setup

Billing (billing.ts)

/billing — manage Nous remote spending — buy credits, auto-reload, limits

Session (session.ts)

/model, /sessions (aliases /switch, /session, /resume), /bg, /btw, /image, /personality, /compress, /branch (alias /fork), /voice, /skin, /indicator, /yolo, /reasoning, /fast, /busy, /verbose, /usage

Ops (ops.ts)

/stop, /reload-mcp (alias /reload_mcp), /reload, /browser, /rollback, /agents (alias /tasks), /replay, /replay-diff, /skills, /reload-skills (alias /reload_skills), /plugins, /tools

Credits (credits.ts)

/credits — Nous credit balance and browser top-up

Setup (setup.ts)

/setup — launches external hermes setup wizard, suspends Ink while it runs

Debug (debug.ts)

/heapdump, /mem — V8 memory diagnostics


Anything not matched above falls through to:

  1. slash.exec
  2. command.dispatch

That lets Python own aliases, plugins, skills, and registry-backed commands without duplicating the logic in the TUI.

Event surface

Primary event types the client handles today:

Event Payload
gateway.ready { skin? }
skin.changed { skin }
session.info session metadata for banner + tool/skill panels
message.start start assistant streaming
message.delta { text, rendered? }
message.complete { text, rendered?, usage, status }
thinking.delta { text }
reasoning.delta { text, verbose? }
reasoning.available { text, verbose? }
status.update { kind, text }
notification.show { id, key, kind, level, text, ttl_ms? }
notification.clear { key }
tool.start { tool_id, name, context?, args_text? }
tool.generating { name }
tool.progress { name, preview }
tool.complete { tool_id, name, error?, summary?, duration_s?, inline_diff?, todos? }
request.cancel { id, method, reason } clears the withdrawn server→client request
background.complete { task_id, text }
billing.step_up.verification { verification_url, user_code }
review.summary { text }
browser.progress { message }
voice.status { state }
voice.transcript { text, no_speech_limit? }
subagent.spawn_requested { subagent_id?, task_index, goal?, depth?, parent_id? }
subagent.start { subagent_id?, task_index, goal?, depth?, parent_id? }
subagent.thinking { text }
subagent.tool { tool_name?, tool_preview?, text? }
subagent.progress { text }
subagent.complete { status, summary?, text?, duration_seconds? }
error { message }
gateway.stderr synthesized from child stderr
gateway.protocol_error synthesized from malformed stdout
gateway.start_timeout { cwd?, python?, stderr_tail? }

Theme model

The client starts with DEFAULT_THEME from theme.ts, then merges in gateway skin data from gateway.ready.

Current branding overrides:

  • agent name
  • prompt symbol
  • welcome text
  • goodbye text

Current color overrides:

  • banner title, accent, border, body, dim
  • label, ok, error, warn

branding.tsx uses those values for the logo, session panel, and update notice.

File map

ui-tui/
  packages/hermes-ink/   forked Ink renderer (local dep)
  src/
    entry.tsx            TTY gate + render()
    app.tsx              top-level Ink tree, composes src/app/*
    gatewayClient.ts     child process + JSON-RPC bridge
    gatewayTypes.ts      gateway event and RPC response type definitions
    theme.ts             theme colors and skin merge
    banner.ts            ASCII art renderer (parses Rich color tags)
    types.ts             shared client-side types (ActiveTool, Msg, etc.)

    app/
      createGatewayEventHandler.ts  event → state mapping
      createSlashHandler.ts         local slash dispatch
      delegationStore.ts            nanostore for subagent spawning caps and overlay accordion state
      gatewayContext.tsx            React context for gateway client
      gatewayRecovery.ts            crash-recovery budget: respawn+resume capped to 3 attempts / 60 s
      inputSelectionStore.ts        nanostore exposing the active text-input selection handle
      interfaces.ts                 internal interfaces (ComposerActions, GatewayRpc, etc.)
      overlayStore.ts               nanostores for overlay state
      scroll.ts                     viewport scroll with text-selection anchor sync
      setupHandoff.ts               launches external hermes setup, suspends Ink while it runs
      spawnHistoryStore.ts          ring buffer of finished subagent fan-out snapshots
      turnController.ts             stateful turn lifecycle driver (streaming, tools, reasoning)
      turnStore.ts                  nanostore for turn state (streaming, tools, reasoning, subagents)
      uiStore.ts                    nanostores for UI flags (busy, sid, mouseTracking, etc.)
      useComposerState.ts           draft + multiline buffer + queue editing
      useConfigSync.ts              config polling and MCP reload on mtime change
      useInputHandlers.ts           keypress routing
      useLongRunToolCharms.ts       ambient activity messages for tools running longer than 8 s
      useMainApp.ts                 top-level composition hook
      useSessionLifecycle.ts        session create / resume / activate / close
      useSubmission.ts              message send, shell exec, interpolation, busy-input-mode dispatch

      slash/
        types.ts                    SlashCommand interface and SlashRunCtx execution context
        registry.ts                 SLASH_COMMANDS assembly and findSlashCommand lookup
        commands/
          billing.ts                /billing — manage Nous remote spending
          core.ts                   general TUI commands
          credits.ts                /credits
          debug.ts                  /heapdump, /mem
          ops.ts                    operations commands
          session.ts                session and agent commands
          setup.ts                  /setup wizard

    components/
      activeSessionSwitcher.tsx  active session switch overlay
      agentsOverlay.tsx          subagent delegation overlay
      appChrome.tsx              status bar, input row, completions
      appLayout.tsx              top-level layout composition
      appOverlays.tsx            overlay routing (pickers, prompts)
      billingOverlay.tsx         billing overlay
      branding.tsx               banner + session summary
      fpsOverlay.tsx             FPS debug overlay
      helpHint.tsx               contextual help hint
      markdown.tsx               Markdown-to-Ink renderer
      maskedPrompt.tsx           masked input for sudo / secrets
      messageLine.tsx            transcript rows
      modelPicker.tsx            model switch picker
      overlayControls.tsx        shared overlay control buttons
      pluginsHub.tsx             plugins hub overlay
      prompts.tsx                approval + clarify flows
      queuedMessages.tsx         queued input preview
      skillsHub.tsx              skills hub overlay
      streamingAssistant.tsx     live streaming assistant row
      streamingMarkdown.tsx      streaming Markdown renderer
      textInput.tsx              custom line editor
      themed.tsx                 theme-aware wrapper
      thinking.tsx               spinner, reasoning, tool activity
      todoPanel.tsx              todo list panel

    config/
      env.ts                     environment variable resolution and Termux/mouse defaults
      limits.ts                  paste size, live-render and history limits
      timing.ts                  streaming batch and debounce timing constants

    content/
      charms.ts                  ambient activity strings for long-running tools
      faces.ts                   agent face / kaomoji pool
      fortunes.ts                /fortune quote pool
      hotkeys.ts                 platform-aware hotkey display strings
      placeholders.ts            rotating input placeholder strings
      setup.ts                   setup-required panel content
      verbs.ts                   tool activity verb map (browser → browsing, etc.)

    domain/
      blockLayout.ts             block layout and lead-gap helpers
      details.ts                 details visibility mode resolution (hidden/collapsed/expanded)
      messages.ts                message formatting and transcript helpers
      paths.ts                   cwd shortening and path display helpers
      providers.ts               provider display name helpers
      roles.ts                   message role color and label helpers
      slash.ts                   slash command parsing and TUI session model flag
      usage.ts                   token usage zero value and helpers
      viewport.ts                viewport height estimation helpers

    hooks/
      useCompletion.ts           tab completion (slash + path)
      useGitBranch.ts            current git branch via child_process execFile
      useInputHistory.ts         persistent history navigation
      useQueue.ts                queued message management
      useVirtualHistory.ts       virtual list scroll and height tracking

    lib/
      circularBuffer.ts          fixed-size generic ring buffer
      clipboard.ts               clipboard read / write via child_process
      editor.ts                  $EDITOR launch, PATH resolution, and Ink suspend
      emoji.ts                   emoji and variation selector width helpers
      externalCli.ts             external CLI subprocess launcher
      externalLink.ts            open URLs in the system browser
      forceTruecolor.ts          24-bit truecolor override before chalk imports
      fpsStore.ts                Ink frame FPS tracker nanostore
      fuzzy.ts                   lightweight fuzzy subsequence scorer
      gracefulExit.ts            clean shutdown with failsafe timeout
      history.ts                 persistent input history (read/append to disk)
      inputMetrics.ts            input width and wrap metrics
      liveProgress.ts            todo helpers and tool-shelf message assembly
      mathUnicode.ts             best-effort LaTeX → Unicode for inline math
      memory.ts                  V8 heap snapshot and diagnostics helpers
      memoryMonitor.ts           automatic heap-dump trigger on high usage
      messages.ts                transcript message append helpers
      openExternalUrl.ts         platform-aware URL opener (macOS/Linux/Windows)
      osc52.ts                   OSC 52 terminal clipboard copy sequence
      parentLog.ts               append-only log to ~/.hermes/tui-parent.log
      perfPane.tsx               FPS / render perf overlay pane
      platform.ts                platform-aware keybinding and SSH detection helpers
      precisionWheel.ts          high-precision scroll wheel with sticky-frame budget
      prompt.ts                  composer prompt text helpers (Termux-safe)
      reasoning.ts               reasoning tag detection and split helpers
      rpc.ts                     JSON-RPC result and command dispatch helpers
      subagentTree.ts            subagent tree flattening and aggregate helpers
      syntax.ts                  syntax token types and theme-aware highlighting
      terminalModes.ts           terminal mode reset sequences (kitty, mouse, etc.)
      terminalParity.ts          VSCode-like terminal detection and hint helpers
      terminalSetup.ts           IDE keybinding config file install helpers
      termux.ts                  Termux platform detection helpers
      text.ts                    text helpers, ANSI detection, tool trail builders
      todo.ts                    todo item tone and display helpers
      viewportStore.ts           viewport height nanostore via ScrollBoxHandle
      virtualHeights.ts          virtual list row height estimation
      wheelAccel.ts              scroll wheel acceleration state machine

    protocol/
      interpolation.ts           {!cmd} inline shell interpolation regex and helpers
      paste.ts                   bracketed paste snippet token regex

    types/
      hermes-ink.d.ts            type declarations for @hermes/ink

    __tests__/                   vitest suite

Related Python side:

tui_gateway/
  entry.py               stdio entrypoint
  server.py              RPC handlers and session logic
  render.py              optional rich/ANSI bridge
  slash_worker.py        persistent HermesCLI subprocess for slash commands